© 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. 3360
    Prev
    Next
    INDEX
    Explanations

    links or URLs ending with specific symbols and numbers

    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
    160
    +0.13
    0.5%
    113
    +0.13
    0.5%
    514
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    20
    +0.13
    0.02
    742
    +0.13
    0.02
    147
    +0.13
    0.02
    Negative Logits
    iddled
    -0.92
    Ò
    -0.89
    eredith
    -0.88
     staggered
    -0.86
     interf
    -0.84
    EStream
    -0.82
    xtap
    -0.80
    unicip
    -0.79
     grap
    -0.78
    ietal
    -0.77
    POSITIVE LOGITS
    CVE
    0.97
    ll
    0.97
    tv
    0.96
    AppData
    0.95
    TIT
    0.94
    edi
    0.94
    username
    0.92
    uve
    0.88
    steamapps
    0.83
    si
    0.82
    Activations Density 0.110%

    No Known Activations