© 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. 18823
    Prev
    Next
    INDEX
    Explanations

    mentions of societal issues or controversies

    oai_token-act-pair · gpt-3.5-turbo

    references to incidents involving legal issues or controversies

    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
    yip
    -0.78
     equivalents
    -0.72
    rax
    -0.71
    semble
    -0.69
    ovy
    -0.69
     export
    -0.69
    zbollah
    -0.67
     flavour
    -0.66
    inctions
    -0.65
    capacity
    -0.63
    POSITIVE LOGITS
    âĢ
    1.40
     âĢ
    1.20
     his
    1.09
     TMZ
    1.08
    ¶
    0.97
    âľ
    0.97
     he
    0.97
    his
    0.92
    âĸ
    0.91
    His
    0.87
    Activations Density 0.748%

    No Known Activations