© 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. 3-RES-JB
    11. 15108
    Prev
    Next
    INDEX
    Explanations

    import statements in code

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "import" typically related to programming or software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    peak
    -0.89
    creen
    -0.81
    cale
    -0.76
    wagen
    -0.71
    bps
    -0.71
    avers
    -0.68
    eenth
    -0.67
    paces
    -0.66
    etheless
    -0.65
    retch
    -0.64
    POSITIVE LOGITS
    antly
    1.12
    Import
    0.96
    unity
    0.91
    import
    0.89
     import
    0.85
    urer
    0.85
    uren
    0.84
    urers
    0.84
    ure
    0.80
     Import
    0.80
    Activations Density 0.010%

    No Known Activations