© 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. 10-RES-JB
    11. 13954
    Prev
    Next
    INDEX
    Explanations

    times and durations

    oai_token-act-pair · gpt-3.5-turbo

    TV show timings and schedules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    luaj
    -0.84
    cig
    -0.83
    saf
    -0.78
    rodu
    -0.76
    ween
    -0.76
    Choice
    -0.76
    Cub
    -0.73
    cigarettes
    -0.72
    bleacher
    -0.71
    Filter
    -0.71
    POSITIVE LOGITS
     PM
    1.69
     AM
    1.43
    PM
    1.30
     pm
    1.25
     EDT
    1.10
     PST
    1.04
    pm
    1.03
     GMT
    1.00
     PDT
    1.00
     PT
    0.98
    Activations Density 0.013%

    No Known Activations