© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 7839
    Prev
    Next
    INDEX
    Explanations

    programming code patterns related to printing and returning values

    oai_token-act-pair · gpt-3.5-turbo

    programming-related command statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rated
    -0.76
    isconsin
    -0.69
    visors
    -0.68
    valued
    -0.67
    lain
    -0.66
    ldom
    -0.66
    emouth
    -0.65
    wana
    -0.65
    rients
    -0.65
    allic
    -0.64
    POSITIVE LOGITS
    Skip
    0.83
    Incre
    0.74
    ((
    0.74
     ((
    0.74
     "\
    0.70
     Skip
    0.69
     len
    0.66
     static
    0.65
     sizeof
    0.65
     "$
    0.65
    Activations Density 0.050%

    No Known Activations