© 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. 18760
    Prev
    Next
    INDEX
    Explanations

    where individuals have contributed to a report or story

    oai_token-act-pair · gpt-3.5-turbo

    credits to contributors of a report or story

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Mods
    -0.82
     Majesty
    -0.68
    é¾įå¥ij士
    -0.67
    stones
    -0.67
     thous
    -0.64
    士
    -0.64
    Īè
    -0.62
     rapists
    -0.60
    Glass
    -0.59
     Maiden
    -0.59
    POSITIVE LOGITS
    enhagen
    0.83
    alysed
    0.77
    inion
    0.76
    trak
    0.73
    cerpt
    0.71
     editorial
    0.70
     Coverage
    0.69
    anamo
    0.67
    ortium
    0.66
     contributed
    0.66
    Activations Density 0.091%

    No Known Activations