© 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. 6855
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a complete set of information or resources necessary for a task or situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to essential information or requirements

    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
     gulf
    -0.66
    izon
    -0.64
    hov
    -0.61
     delinqu
    -0.59
    ishers
    -0.58
     Marlins
    -0.57
    cession
    -0.57
    furt
    -0.56
     Lowell
    -0.56
     Laksh
    -0.56
    POSITIVE LOGITS
    lessly
    0.81
     to
    0.79
    n
    0.76
    ioned
    0.72
     Citation
    0.70
    rous
    0.68
    rals
    0.67
    Gaming
    0.63
    cale
    0.62
    ynes
    0.61
    Activations Density 0.060%

    No Known Activations