© 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. 1-RES-JB
    11. 9401
    Prev
    Next
    INDEX
    Explanations

    references to dangerous driving behavior

    oai_token-act-pair · gpt-3.5-turbo

    references to ongoing situations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ansson
    -0.79
    ovies
    -0.68
    aeus
    -0.67
    itsch
    -0.66
     Zucker
    -0.65
    essional
    -0.64
     Io
    -0.64
    Roberts
    -0.64
    EVA
    -0.64
    INST
    -0.63
    POSITIVE LOGITS
    versions
    0.69
    punk
    0.66
    cies
    0.65
     tar
    0.63
     breaching
    0.62
    tha
    0.60
    grading
    0.60
    finding
    0.58
    resa
    0.58
    rave
    0.57
    Activations Density 0.000%

    No Known Activations