© 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. 8-RES-JB
    11. 6166
    Prev
    Next
    INDEX
    Explanations

    words related to specifying conditions or requirements

    oai_token-act-pair · gpt-3.5-turbo

    clauses or terms related to conditions and stipulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tycoon
    -0.87
    ica
    -0.77
    ined
    -0.76
    士
    -0.73
    ively
    -0.69
    ic
    -0.68
    ive
    -0.65
    ocker
    -0.63
     Roe
    -0.62
     Rocks
    -0.61
    POSITIVE LOGITS
    ulative
    0.99
    pillar
    0.97
    pill
    0.81
    enei
    0.78
    endiary
    0.77
    nis
    0.76
    intelligence
    0.76
    spread
    0.75
    limits
    0.75
    pole
    0.73
    Activations Density 0.112%

    No Known Activations