© 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. 7675
    Prev
    Next
    INDEX
    Explanations

    terms referencing perspective or stance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to contextual considerations and evaluations

    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
    ModLoader
    -0.77
    ten
    -0.70
    tin
    -0.69
     tyr
    -0.67
    ãĥ³ãĤ¸
    -0.67
    kered
    -0.65
    regor
    -0.64
    Recipe
    -0.64
     laun
    -0.63
    thumbnails
    -0.62
    POSITIVE LOGITS
     alone
    0.97
     Leone
    0.63
     onwards
    0.62
     belongs
    0.61
    SPONSORED
    0.60
    ativity
    0.60
     coupled
    0.58
     Schneider
    0.58
    ioxide
    0.56
    ,
    0.56
    Activations Density 0.075%

    No Known Activations