© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 2081
    Prev
    Next
    INDEX
    Explanations

    terms related to freedoms and rights, such as freedom of religion, freedom from want, freedom of speech, and freedom of choice

    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
    108
    +0.16
    0.5%
    234
    +0.15
    0.5%
    747
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    234
    +0.16
    0.04
    747
    +0.15
    0.03
    108
    +0.15
    0.04
    Negative Logits
     Twice
    -0.99
    ashtra
    -0.91
    hya
    -0.91
    kh
    -0.91
     Bog
    -0.90
     unfocusedRange
    -0.89
    dule
    -0.89
    iaz
    -0.88
    terday
    -0.88
     Cull
    -0.87
    POSITIVE LOGITS
    enhagen
    1.26
    anding
    1.15
     roam
    1.07
    ãĤ¦
    1.02
    expression
    1.00
    ercise
    0.96
    PLAY
    0.94
     loose
    0.92
    arters
    0.92
    eco
    0.92
    Activations Density 0.644%

    No Known Activations