© 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. 9-RES-JB
    11. 1052
    Prev
    Next
    INDEX
    Explanations

    mention of the rock band "The Dead" or related terms associated with the band

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the band "The Grateful Dead"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    efully
    -0.78
    alysed
    -0.77
    antly
    -0.76
    uration
    -0.75
    ĸļ
    -0.69
     aur
    -0.66
    xual
    -0.65
    fty
    -0.65
    é¾įåĸļ士
    -0.63
     Vik
    -0.63
    POSITIVE LOGITS
    spin
    1.09
    liest
    1.07
    lift
    0.97
    wood
    0.93
    pool
    0.91
    ward
    0.90
     Redemption
    0.89
    adder
    0.84
     Dead
    0.83
    roots
    0.83
    Activations Density 0.039%

    No Known Activations