© 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. 2-RES-JB
    11. 670
    Prev
    Next
    INDEX
    Explanations

    the specific character sequence "icken"

    oai_token-act-pair · gpt-4-turbo

    mentions of the name "Hickenlooper"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual, likely a public figure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     4090
    -0.68
     Columb
    -0.67
     surv
    -0.65
    oret
    -0.64
    atography
    -0.63
     miracle
    -0.62
     nom
    -0.62
    tical
    -0.62
     cryst
    -0.60
     reversible
    -0.60
    POSITIVE LOGITS
    ergy
    1.04
    icken
    1.02
    backer
    1.02
    issance
    0.88
    bats
    0.87
    hs
    0.86
    cil
    0.86
    fold
    0.80
    heid
    0.80
    cies
    0.79
    Activations Density 0.011%

    No Known Activations