© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 35303
    Prev
    Next
    INDEX
    Explanations

    mentions of social justice issues and activism related to discrimination or profiling based on gender identity or sexual orientation

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.28
    1.7%
    393
    +0.18
    1.1%
    36
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.28
    0.37
    393
    +0.18
    0.29
    159
    +0.17
    0.17
    Negative Logits
    anism
    -0.75
    agree
    -0.64
    agents
    -0.59
    evidence
    -0.58
    ['
    -0.58
     knows
    -0.57
    acid
    -0.56
    Attempts
    -0.56
    agent
    -0.55
    Thom
    -0.54
    POSITIVE LOGITS
     plethora
    0.89
     slew
    0.85
     handful
    0.84
     whopping
    0.82
     bunch
    0.79
     glimpse
    0.78
     few
    0.77
     sizable
    0.77
     sizeable
    0.76
     handy
    0.76
    Activations Density 10.879%

    No Known Activations