© 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. 36118
    Prev
    Next
    INDEX
    Explanations

    information related to space exploration and space technology

    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
    288
    +0.16
    0.7%
    575
    +0.13
    0.6%
    290
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.16
    0.08
    48
    +0.13
    0.08
    308
    +0.12
    0.06
    Negative Logits
    usted
    -0.80
    ombie
    -0.79
    ãĥĥãĥĪ
    -0.76
    heit
    -0.75
    ublic
    -0.75
    uminati
    -0.73
    irez
    -0.73
     behold
    -0.73
     presumptive
    -0.71
    venge
    -0.71
    POSITIVE LOGITS
    craft
    0.98
     Shuttle
    0.93
     Patrol
    0.92
     Station
    0.92
     Advisor
    0.92
     Operations
    0.91
     Matters
    0.89
    Engineers
    0.87
    flight
    0.86
     Agency
    0.85
    Activations Density 3.925%

    No Known Activations