© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 18784
    Prev
    Next
    INDEX
    Explanations

    vulgar or profane language

    oai_token-act-pair · gpt-3.5-turbo

    occurrences and expressions of the word "shit."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HCR
    -0.78
    fman
    -0.76
    gary
    -0.75
    ================================
    -0.71
    BIL
    -0.70
    PsyNetMessage
    -0.69
     Expend
    -0.68
    Minor
    -0.65
    NetMessage
    -0.64
    Specific
    -0.62
    POSITIVE LOGITS
    bags
    0.95
    heads
    0.94
    loads
    0.94
    wit
    0.89
    storm
    0.89
    posts
    0.89
    shots
    0.87
    lord
    0.86
    shit
    0.85
    dump
    0.82
    Activations Density 0.021%

    No Known Activations