© 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. 1-RES-JB
    11. 9363
    Prev
    Next
    INDEX
    Explanations

    phrases that are marked or highlighted with special characters like quotation marks or angle brackets

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks or other similar typographical symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itably
    -0.82
     Burnett
    -0.73
    enough
    -0.71
    itable
    -0.70
    liest
    -0.69
    姫
    -0.69
    idge
    -0.67
    ellen
    -0.62
     tuna
    -0.61
     purse
    -0.61
    POSITIVE LOGITS
     «
    1.17
    «
    1.01
    CLASSIFIED
    0.90
    ĨĴ
    0.88
    Prev
    0.85
    resy
    0.79
    âĢ¢âĢ¢
    0.75
    grave
    0.74
    tal
    0.70
     Obj
    0.69
    Activations Density 0.012%

    No Known Activations