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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 34040
    Prev
    Next
    INDEX
    Explanations

    phrases related to advocating for rights and standing up for beliefs

    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
    481
    +0.20
    1.2%
    447
    +0.17
    1.0%
    385
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.20
    0.29
    481
    +0.17
    0.27
    362
    +0.08
    0.13
    Negative Logits
    ipment
    -0.55
    sterdam
    -0.55
    requisite
    -0.55
    lav
    -0.52
    velop
    -0.51
    ueller
    -0.51
    Course
    -0.51
    availability
    -0.51
     simulator
    -0.51
    artment
    -0.49
    POSITIVE LOGITS
    ĪĴ
    0.71
     whistleblowers
    0.69
     courageous
    0.65
     brave
    0.65
     injust
    0.63
     Against
    0.62
     principled
    0.61
     boldly
    0.60
     courage
    0.58
     humanity
    0.57
    Activations Density 12.373%

    No Known Activations