© 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. 11-RES-JB
    11. 17728
    Prev
    Next
    INDEX
    Explanations

    comparisons of quantity or degree, such as "as much," "more of," "considerably more," "too much," and "little."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating quantities or degrees of influence and power

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reporter
    -0.72
    assis
    -0.71
    Ĥª
    -0.70
    ploy
    -0.69
    Chel
    -0.68
     Digest
    -0.68
    cos
    -0.68
    xtap
    -0.66
    acle
    -0.66
    atri
    -0.65
    POSITIVE LOGITS
     clout
    1.10
     patience
    1.04
     sympathy
    1.01
     latitude
    0.99
     recourse
    0.98
     confidence
    0.97
     leverage
    0.95
     faith
    0.95
     doubts
    0.94
     trouble
    0.93
    Activations Density 0.153%

    No Known Activations