© 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. 13461
    Prev
    Next
    INDEX
    Explanations

    words related to people's names or places

    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
    50
    +0.15
    0.5%
    41
    +0.15
    0.5%
    314
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    41
    +0.15
    0.07
    406
    +0.15
    0.07
    46
    +0.14
    0.06
    Negative Logits
    FORMATION
    -0.97
    Whereas
    -0.89
     Malays
    -0.89
     FTC
    -0.88
     guiActiveUn
    -0.87
     partName
    -0.86
    RFC
    -0.84
    effic
    -0.84
     facets
    -0.82
    \/\/
    -0.82
    POSITIVE LOGITS
    levard
    1.59
    lehem
    1.41
    pillar
    1.40
    apest
    1.39
    rill
    1.32
    aneers
    1.23
    hammad
    1.22
    reau
    1.22
    ause
    1.18
    etooth
    1.16
    Activations Density 1.543%

    No Known Activations