© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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 Local
    9. 6-RES_SCL-AJT
    11. 45733
    Prev
    Next
    INDEX
    Explanations

    words related to envelopes and items that are contained within envelopes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    549
    +0.11
    0.5%
    707
    +0.10
    0.5%
    623
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    709
    +0.11
    0.11
    301
    +0.10
    0.09
    288
    +0.09
    0.21
    Negative Logits
     Titans
    -0.73
    ãĤ´ãĥ³
    -0.72
    anooga
    -0.71
    nesota
    -0.66
    utsche
    -0.65
    aldi
    -0.62
     Ath
    -0.62
     Texans
    -0.61
    Stars
    -0.60
     Osw
    -0.59
    POSITIVE LOGITS
    velop
    0.97
     envelope
    0.91
    eers
    0.85
    stakes
    0.85
    mble
    0.84
    nuts
    0.82
    ingly
    0.82
     envelop
    0.81
    erella
    0.74
    pread
    0.72
    Activations Density 8.880%

    No Known Activations