© 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. 2-RES-JB
    11. 12772
    Prev
    Next
    INDEX
    Explanations

    numerical values in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    percentages and numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raints
    -0.73
    andestine
    -0.72
     tremend
    -0.70
    uesday
    -0.68
    achus
    -0.66
     Ens
    -0.62
    ihad
    -0.62
     wholes
    -0.61
     caring
    -0.61
    iosyn
    -0.61
    POSITIVE LOGITS
    ãĥ¼ãĥ³
    0.72
    bis
    0.69
    İ
    0.69
    394
    0.69
    245
    0.68
     attRot
    0.67
    df
    0.67
    449
    0.67
    195
    0.66
    595
    0.65
    Activations Density 0.285%

    No Known Activations