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. 7-RES-JB
    6. 23245
    Prev
    Next
    INDEX
    Explanations

    expressions related to criticism or negative judgment

    oai_token-act-pair · gpt-3.5-turbo

    themes of boldness and audacity in actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    accompanied
    -0.73
    oother
    -0.71
    ertility
    -0.69
    uese
    -0.65
    ertain
    -0.64
    acion
    -0.64
    ilingual
    -0.63
     nightly
    -0.63
    rose
    -0.63
    pop
    -0.63
    POSITIVE LOGITS
     coward
    1.04
     omission
    0.95
     arrogance
    0.94
     cowardly
    0.93
     stupidity
    0.92
     malice
    0.89
     motives
    0.85
     folly
    0.83
     manslaughter
    0.82
     negligence
    0.82
    Activations Density 0.437%

    No Known Activations