© 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. 11932
    Prev
    Next
    INDEX
    Explanations

    phrases or descriptions related to political events and governmental actions

    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
    190
    +0.15
    0.5%
    272
    +0.14
    0.4%
    424
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    436
    +0.15
    0.06
    362
    +0.14
    0.07
    190
    +0.14
    0.07
    Negative Logits
    anwhile
    -1.02
    etsk
    -1.00
    pload
    -0.97
    pta
    -0.94
    skirts
    -0.94
    Ô
    -0.93
    vati
    -0.92
    ":""},{"
    -0.92
     Valhalla
    -0.91
    ertodd
    -0.90
    POSITIVE LOGITS
     magnitude
    1.28
     persuasion
    1.24
     proportions
    1.13
     il
    1.07
     stature
    1.07
     importance
    1.07
     renown
    1.06
    interest
    1.06
     origin
    1.03
     utmost
    1.03
    Activations Density 2.486%

    No Known Activations