© 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. 11121
    Prev
    Next
    INDEX
    Explanations

    names of well-known tech companies

    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
    175
    +0.03
    0.5%
    245
    +0.02
    0.5%
    493
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.03
    0.03
    284
    +0.02
    0.03
    373
    +0.02
    -0.01
    Negative Logits
     Kings
    -0.16
    Merc
    -0.16
     weary
    -0.15
    Oak
    -0.15
     Tempest
    -0.14
     lab
    -0.14
     dwelling
    -0.14
     contact
    -0.14
     Reaper
    -0.14
     Morrow
    -0.14
    POSITIVE LOGITS
    onal
    0.18
    >]
    0.17
    thumbnails
    0.17
    natureconservancy
    0.16
    ãĤ¨ãĥ«
    0.16
    arat
    0.16
    acci
    0.16
    erie
    0.16
     Rampage
    0.15
    uation
    0.15
    Activations Density 0.100%

    No Known Activations