© 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. 11-RES-JB
    11. 18787
    Prev
    Next
    INDEX
    Explanations

    numerical descriptions of quantities such as counts or measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and specific time indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     swearing
    -0.68
     fluct
    -0.64
     swear
    -0.61
     fart
    -0.61
     "$:/
    -0.58
     toler
    -0.57
    Ĥİ
    -0.55
     conve
    -0.54
    theless
    -0.54
     distant
    -0.54
    POSITIVE LOGITS
    ½
    1.02
     ½
    1.00
    Pac
    0.94
    WD
    0.92
    UP
    0.88
    LT
    0.88
    GW
    0.84
    RM
    0.83
    200
    0.83
    DP
    0.83
    Activations Density 0.111%

    No Known Activations