© 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. 17446
    Prev
    Next
    INDEX
    Explanations

    patterns or repetitions in data

    oai_token-act-pair · gpt-3.5-turbo

    references to recurring themes or trends

    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
    grim
    -0.78
    igious
    -0.73
    ilings
    -0.71
    zona
    -0.68
    minent
    -0.68
    =-=-=-=-
    -0.67
    glomer
    -0.66
    UST
    -0.66
    igion
    -0.65
    ocado
    -0.65
    POSITIVE LOGITS
     pattern
    1.21
     patterns
    1.12
     Pattern
    1.10
    Pattern
    1.03
    pattern
    1.00
     Patterns
    1.00
    eering
    0.98
    ĸļ
    0.97
     repeats
    0.81
    atile
    0.75
    Activations Density 0.007%

    No Known Activations