© 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. 1041
    Prev
    Next
    INDEX
    Explanations

    verbs and adjectives related to mental processes like thinking, remembering, and considering

    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
    684
    +0.07
    0.5%
    722
    +0.06
    0.4%
    68
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.07
    0.05
    122
    +0.06
    0.05
    641
    +0.06
    0.05
    Negative Logits
    aneers
    -0.44
    rongh
    -0.44
    alach
    -0.44
    BuyableInstoreAndOnline
    -0.43
    etheus
    -0.43
    obyl
    -0.42
    aura
    -0.42
    Baltimore
    -0.41
    awar
    -0.41
    ilings
    -0.40
    POSITIVE LOGITS
     GOODMAN
    0.53
    ĸ
    0.48
    eteen
    0.46
    ĵĺ
    0.46
    enance
    0.45
    orial
    0.44
    itial
    0.42
    xual
    0.42
    ı
    0.41
    rils
    0.41
    Activations Density 0.496%

    No Known Activations