© 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. 14118
    Prev
    Next
    INDEX
    Explanations

    analogies and provide context and perspective on numerical information

    oai_token-act-pair · gpt-3.5-turbo

    statements that provide comparisons or analogies to clarify complex concepts

    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
    sbm
    -0.73
    "},"
    -0.68
    cffff
    -0.61
    ãĥı
    -0.61
    abb
    -0.57
    arnaev
    -0.56
    NetMessage
    -0.55
     deposits
    -0.55
    affiliated
    -0.54
    lected
    -0.53
    POSITIVE LOGITS
     sake
    0.79
     please
    0.78
     congr
    0.77
    ,
    0.76
     let
    0.75
    please
    0.75
    :
    0.72
    vity
    0.72
     suffice
    0.71
     consider
    0.70
    Activations Density 0.141%

    No Known Activations