© 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 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. 12203
    Prev
    Next
    INDEX
    Explanations

    financial segments or divisions within a company

    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
    288
    +0.19
    0.7%
    587
    +0.13
    0.5%
    161
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.15
    540
    +0.13
    0.10
    575
    +0.12
    0.09
    Negative Logits
    fet
    -0.96
     Predators
    -0.84
    ITH
    -0.77
     mother
    -0.77
    ILLE
    -0.76
     opio
    -0.75
    ullivan
    -0.74
     Fighters
    -0.74
    aina
    -0.73
    verbs
    -0.72
    POSITIVE LOGITS
    naire
    1.17
    ials
    1.06
    al
    0.97
    ation
    0.94
    ial
    0.92
    ed
    0.91
    edly
    0.90
    ational
    0.89
    nered
    0.89
    naires
    0.89
    Activations Density 1.902%

    No Known Activations