© 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. 2018
    Prev
    Next
    INDEX
    Explanations

    text messages and communication-related activities

    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
    361
    +0.14
    0.5%
    726
    +0.11
    0.4%
    547
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    217
    +0.14
    0.05
    361
    +0.11
    0.06
    132
    +0.11
    0.05
    Negative Logits
     rigging
    -0.87
    effic
    -0.84
    aho
    -0.81
    tis
    -0.81
     masc
    -0.80
     Trials
    -0.80
    adders
    -0.76
    addons
    -0.74
    rimination
    -0.73
    jury
    -0.72
    POSITIVE LOGITS
    mail
    1.20
     inbox
    1.15
     invitations
    1.14
     correspondence
    1.10
    mails
    1.07
     memos
    1.02
     messages
    1.02
     memo
    1.00
     Emails
    1.00
     addressed
    1.00
    Activations Density 1.066%

    No Known Activations