Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 9416
    Prev
    Next
    INDEX
    Explanations

    phrases expressing reluctance or hesitation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire or intent not to do something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issance
    -0.74
    hiba
    -0.72
    terms
    -0.72
    utical
    -0.72
    strength
    -0.71
    ammy
    -0.70
    VERTISEMENT
    -0.69
    manship
    -0.69
    figure
    -0.67
    icol
    -0.66
    POSITIVE LOGITS
     anymore
    0.96
     anybody
    0.88
     necessarily
    0.82
     nor
    0.80
     anything
    0.79
     anyone
    0.77
    cha
    0.77
     any
    0.72
    reprene
    0.72
     revenge
    0.71
    Activations Density 0.034%

    No Known Activations