© 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. 7-RES-JB
    11. 7231
    Prev
    Next
    INDEX
    Explanations

    words related to imposing restrictions or limitations

    oai_token-act-pair · gpt-3.5-turbo
    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
    FORE
    -0.75
    Äĩ
    -0.73
    acht
    -0.71
    ublic
    -0.67
    Sham
    -0.66
    "},{"
    -0.65
    itched
    -0.64
    ¢
    -0.64
    ilon
    -0.63
    },"
    -0.62
    POSITIVE LOGITS
     mobility
    0.88
     access
    0.87
     withdrawals
    0.80
     discretionary
    0.78
     proliferation
    0.76
    ively
    0.76
     visibility
    0.76
     autonomy
    0.75
    orously
    0.75
     unrestricted
    0.75
    Activations Density 0.069%

    No Known Activations