© 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. 3167
    Prev
    Next
    INDEX
    Explanations

    words related to hiding, concealing, or encompassing

    oai_token-act-pair · gpt-3.5-turbo

    references to topics related to coverage or the act of providing detailed information on various subjects

    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
    sett
    -0.72
    jet
    -0.72
    failed
    -0.71
    rian
    -0.71
    ellig
    -0.71
    radical
    -0.70
     Sabha
    -0.68
    bra
    -0.67
    nesia
    -0.65
    Sa
    -0.65
    POSITIVE LOGITS
     covering
    1.02
     COVER
    0.93
     covers
    0.87
    utical
    0.82
     Coverage
    0.79
     cover
    0.76
    verage
    0.76
    krit
    0.75
     wip
    0.74
    Cover
    0.72
    Activations Density 0.012%

    No Known Activations