© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 10881
    Prev
    Next
    INDEX
    Explanations

    expressions of disappointment or resigned acceptance

    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
    363
    +0.13
    0.5%
    468
    +0.13
    0.5%
    602
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    88
    +0.13
    0.05
    602
    +0.13
    0.04
    373
    +0.12
    -0.03
    Negative Logits
    omsky
    -0.95
     Cosponsors
    -0.87
    acio
    -0.87
    psons
    -0.86
    rament
    -0.84
    yth
    -0.83
    ":["
    -0.82
    esville
    -0.81
    imble
    -0.81
     Yard
    -0.80
    POSITIVE LOGITS
     dunno
    1.05
     hello
    0.93
     yeah
    0.90
     bye
    0.84
     situational
    0.82
     maybe
    0.81
     intentions
    0.79
     ol
    0.78
     forgive
    0.78
     okay
    0.77
    Activations Density 0.532%

    No Known Activations