© 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. 9-RES-JB
    11. 18502
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons or distinctions

    oai_token-act-pair · gpt-3.5-turbo

    connections or comparisons between ideas or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =(
    -0.70
     ILCS
    -0.70
    !".
    -0.62
    zers
    -0.60
    ãĢį
    -0.60
    .ãĢį
    -0.59
    ((
    -0.58
    .–
    -0.57
    zona
    -0.56
    pointers
    -0.56
    POSITIVE LOGITS
    ILA
    0.62
    onential
    0.59
     understatement
    0.58
     elegance
    0.58
    arious
    0.55
    perfect
    0.53
     diligence
    0.53
    otic
    0.53
     Responsibility
    0.53
    isite
    0.52
    Activations Density 0.387%

    No Known Activations