© 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. 18518
    Prev
    Next
    INDEX
    Explanations

    the word "could" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate potential outcomes or possibilities

    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
    core
    -0.68
    teen
    -0.65
    raint
    -0.65
    ainment
    -0.63
    cies
    -0.62
    jac
    -0.62
     honors
    -0.61
    Maker
    -0.61
    got
    -0.60
    cloth
    -0.60
    POSITIVE LOGITS
     feas
    1.25
     conce
    1.22
     potentially
    1.08
     be
    1.05
     theoretically
    1.01
     hypot
    0.99
     possibly
    0.99
    ivably
    0.94
    yip
    0.93
     easily
    0.92
    Activations Density 0.096%

    No Known Activations