© 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. 12104
    Prev
    Next
    INDEX
    Explanations

    words related to interpersonal interactions and conflicts

    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
    620
    +0.12
    0.5%
    458
    +0.10
    0.4%
    550
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.12
    0.12
    49
    +0.10
    0.11
    665
    +0.10
    0.13
    Negative Logits
    theless
    -0.99
    ccording
    -0.88
     encount
    -0.77
     experien
    -0.74
     rall
    -0.72
    anwhile
    -0.72
    ivably
    -0.71
    osate
    -0.69
     millenn
    -0.69
    quartered
    -0.69
    POSITIVE LOGITS
     whom
    0.86
     theirs
    0.78
     Shap
    0.77
    iHUD
    0.72
     QC
    0.71
    bes
    0.70
    onite
    0.70
    coni
    0.69
     hers
    0.69
    icz
    0.67
    Activations Density 4.496%

    No Known Activations