© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 3303
    Prev
    Next
    INDEX
    Explanations

    words related to legal and political issues

    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
    48
    +0.16
    0.6%
    701
    +0.14
    0.5%
    288
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.16
    0.05
    701
    +0.14
    0.03
    159
    +0.14
    0.03
    Negative Logits
    âķIJâķIJ
    -0.95
    ter
    -0.84
    terday
    -0.84
     Bake
    -0.83
    ettings
    -0.80
    ktop
    -0.79
    ting
    -0.77
    ELL
    -0.77
    hower
    -0.77
    tty
    -0.76
    POSITIVE LOGITS
    itimate
    1.72
    acies
    1.39
    edly
    1.34
    rett
    1.34
    isl
    1.33
    acy
    1.30
    enic
    1.27
    rosc
    1.26
    rants
    1.23
    uin
    1.22
    Activations Density 0.479%

    No Known Activations