© 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. 1-RES-JB
    11. 18635
    Prev
    Next
    INDEX
    Explanations

    mentions of specific document parts or sections labeled as "Part X."

    oai_token-act-pair · gpt-3.5-turbo

    references to parts or sections of a document or report

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arms
    -0.71
     gifted
    -0.68
     mentally
    -0.64
    berman
    -0.61
     throats
    -0.60
    urses
    -0.59
    llular
    -0.59
     kn
    -0.59
    incinn
    -0.59
     crawl
    -0.59
    POSITIVE LOGITS
    icularly
    1.06
    ners
    0.99
    Part
    0.98
     Part
    0.97
    ially
    0.96
    ITION
    0.93
    ition
    0.87
    icipated
    0.84
    nered
    0.84
    ICLE
    0.84
    Activations Density 0.008%

    No Known Activations