© 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. 14065
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers

    oai_token-act-pair · gpt-3.5-turbo

    sports statistics and performance metrics

    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
     newsletters
    -0.58
     caveats
    -0.53
     emails
    -0.49
    mails
    -0.49
     and
    -0.49
    âĢ¢âĢ¢
    -0.48
    $$$$
    -0.47
    rams
    -0.46
     filings
    -0.45
     parentheses
    -0.45
    POSITIVE LOGITS
    ledged
    0.52
    astern
    0.51
    nt
    0.50
    ktop
    0.50
     recognised
    0.50
    uin
    0.50
     Entered
    0.49
    Joined
    0.49
    ãĤ¨ãĥ«
    0.48
    çĶ°
    0.48
    Activations Density 1.103%

    No Known Activations