© 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. 10-RES-JB
    11. 6741
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical settings or locations

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ÂŃ
    -0.52
    aky
    -0.52
    emaker
    -0.50
     frontline
    -0.49
    ussy
    -0.48
    inge
    -0.48
    chuk
    -0.47
    ady
    -0.47
    .*
    -0.47
    ,
    -0.46
    POSITIVE LOGITS
     huh
    0.85
     please
    0.80
     etc
    0.78
    please
    0.76
    govtrack
    0.71
    channelAvailability
    0.68
     meanwhile
    0.66
    flush
    0.66
     however
    0.66
     aka
    0.64
    Activations Density 0.205%

    No Known Activations