© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2221
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical figures

    oai_token-act-pair · gpt-3.5-turbo

    quantitative indicators and recurrent terms related to frequency

    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
    hess
    -0.62
     Clarks
    -0.61
     Features
    -0.60
     Advice
    -0.60
     enthus
    -0.59
    izo
    -0.58
     Honour
    -0.58
     blues
    -0.55
     Journals
    -0.55
    edge
    -0.55
    POSITIVE LOGITS
     year
    1.62
     month
    1.38
    year
    1.27
     decade
    1.19
     week
    1.16
     YEAR
    1.14
     day
    1.09
    month
    1.04
    Year
    1.03
     Year
    1.03
    Activations Density 0.058%

    No Known Activations