© 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 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 6238
    Prev
    Next
    INDEX
    Explanations

    words related to morality and judgment based on certain contextual clues

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    409
    +0.06
    0.5%
    254
    +0.05
    0.5%
    583
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.06
    0.01
    150
    +0.05
    0.01
    568
    +0.05
    0.01
    Negative Logits
    rose
    -0.36
    glass
    -0.35
    éĸ
    -0.34
    arro
    -0.31
     wink
    -0.30
    vir
    -0.30
     Ray
    -0.30
     padded
    -0.30
     Airl
    -0.30
    cone
    -0.29
    POSITIVE LOGITS
    redit
    0.39
    atility
    0.39
    avement
    0.39
    folios
    0.37
     maturity
    0.37
    ":["
    0.37
    TY
    0.36
    comings
    0.36
    izons
    0.35
     redundancy
    0.34
    Activations Density 0.017%

    No Known Activations