© 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. 0-RES-JB
    11. 6693
    Prev
    Next
    INDEX
    Explanations

    words related to strong smells, particularly those that are unpleasant

    oai_token-act-pair · gpt-3.5-turbo

    mentions of substances related to smoking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eag
    -0.76
     Hou
    -0.70
     Giles
    -0.69
     Leh
    -0.68
     constit
    -0.66
     Bridges
    -0.65
     integral
    -0.64
     dur
    -0.63
     inaccessible
    -0.63
     Priebus
    -0.62
    POSITIVE LOGITS
    sm
    4.27
    Sm
    2.15
    smoking
    1.57
    sn
    1.56
     Sm
    1.55
    SM
    1.48
     sm
    1.41
    sw
    1.35
    sp
    1.33
    sf
    1.23
    Activations Density 0.009%

    No Known Activations