© 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. 3135
    Prev
    Next
    INDEX
    Explanations

    phrases indicating inability to perform a specific action

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating negation or inability

    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
    senal
    -0.68
     Actions
    -0.66
    artifacts
    -0.65
    ILA
    -0.65
     Appears
    -0.62
    amy
    -0.60
    esting
    -0.59
    mite
    -0.59
    marks
    -0.58
     Transparency
    -0.58
    POSITIVE LOGITS
     afford
    1.17
     cope
    0.97
     overcome
    0.92
     conceive
    0.91
     muster
    0.90
     convince
    0.90
     foresee
    0.89
     comprehend
    0.86
     persuade
    0.85
     feas
    0.83
    Activations Density 0.113%

    No Known Activations