© 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. 3-RES-JB
    11. 10744
    Prev
    Next
    INDEX
    Explanations

    expressions or interjections conveying surprise, realization, or commentary

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing disbelief or surprise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BILITIES
    -0.88
    ãĥł
    -0.68
    MRI
    -0.67
     abdom
    -0.67
    BIL
    -0.65
    İĭ
    -0.65
    udo
    -0.64
     hypothal
    -0.63
    ially
    -0.62
    thood
    -0.61
    POSITIVE LOGITS
     Witnesses
    0.71
     Pradesh
    0.68
    va
    0.66
    schild
    0.64
    ibaba
    0.63
     wanna
    0.63
     Mistress
    0.62
     Dah
    0.61
    lda
    0.61
     Haku
    0.59
    Activations Density 0.286%

    No Known Activations