© 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. 21379
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving addition

    oai_token-act-pair · gpt-3.5-turbo

    parentheses and numerical operations or expressions within a coded context

    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
     disadvant
    -0.59
     flagship
    -0.58
     timely
    -0.58
     conduc
    -0.58
     pharm
    -0.58
     academic
    -0.57
     cradle
    -0.56
     sustainability
    -0.56
    itory
    -0.55
     sleeper
    -0.55
    POSITIVE LOGITS
    ãĥİ
    1.12
     =>
    0.94
    âķ
    0.79
     Frames
    0.76
    +(
    0.73
    eem
    0.69
    76561
    0.69
    ¢
    0.69
    $,
    0.68
     ==
    0.66
    Activations Density 0.072%

    No Known Activations