© 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. 14669
    Prev
    Next
    INDEX
    Explanations

    phrases related to email subscriptions and opt-out options

    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
    130
    +0.13
    0.4%
    29
    +0.13
    0.4%
    268
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.13
    0.02
    208
    +0.13
    0.02
    500
    +0.13
    0.01
    Negative Logits
     Grimoire
    -1.25
     Surviv
    -1.20
    mania
    -1.09
    amina
    -0.99
     Fam
    -0.97
    rums
    -0.96
     Tac
    -0.96
    pex
    -0.91
     Presence
    -0.90
     Cyn
    -0.90
    POSITIVE LOGITS
     embargo
    1.08
     indemn
    1.05
     emb
    1.05
    icol
    1.02
     unsub
    1.00
    rill
    0.93
    uploads
    0.91
     checkout
    0.91
    imaru
    0.90
     download
    0.90
    Activations Density 0.043%

    No Known Activations