© 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. 9-RES-JB
    11. 15781
    Prev
    Next
    INDEX
    Explanations

    complex statements or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of commas or pauses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Previous
    -0.72
    """
    -0.72
    Write
    -0.69
    ighed
    -0.69
    .--
    -0.68
    !,
    -0.67
    SourceFile
    -0.66
    Ãĥ
    -0.66
     Telescope
    -0.65
    oj
    -0.64
    POSITIVE LOGITS
     somew
    0.78
     downright
    0.69
     utterly
    0.67
     nonexistent
    0.67
     indis
    0.65
     somewhat
    0.64
     fairly
    0.63
     indistinguishable
    0.62
     profoundly
    0.62
     incon
    0.62
    Activations Density 0.107%

    No Known Activations