© 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. 17856
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    instances of hesitation or uncertainty in the text

    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
    microsoft
    -0.63
     extrem
    -0.63
     Franç
    -0.63
     Labrador
    -0.61
    PsyNetMessage
    -0.61
     Miche
    -0.60
     Krug
    -0.60
     Kanye
    -0.59
     Pokémon
    -0.59
     snipp
    -0.59
    POSITIVE LOGITS
    hm
    1.08
    atsu
    0.94
    ilia
    0.91
    mmm
    0.90
    arijuana
    0.88
    nesty
    0.88
    ueller
    0.88
    oyer
    0.87
    fg
    0.86
    asonic
    0.85
    Activations Density 0.019%

    No Known Activations