© 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. 10-RES-JB
    11. 9908
    Prev
    Next
    INDEX
    Explanations

    potential actions or possibilities

    oai_token-act-pair · gpt-3.5-turbo

    expressions of potential or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ainment
    -0.70
    area
    -0.63
    icial
    -0.62
     Lauder
    -0.61
     honors
    -0.58
    core
    -0.58
     Laz
    -0.56
     Remastered
    -0.56
     Kis
    -0.56
    stru
    -0.56
    POSITIVE LOGITS
     feas
    1.26
     conce
    1.16
     easily
    1.14
     theoretically
    1.02
     possibly
    0.99
    ivably
    0.92
     plaus
    0.92
     potentially
    0.91
     hypot
    0.89
     argue
    0.89
    Activations Density 0.116%

    No Known Activations