© 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. 2752
    Prev
    Next
    INDEX
    Explanations

    dates and references to specific individuals or organizations mentioned in a formal context

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation and phrases that indicate a list or sequence

    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
    ndra
    -0.67
    ãĤ¢ãĥ«
    -0.61
    peria
    -0.59
    resa
    -0.59
    aukee
    -0.59
    igers
    -0.58
    Score
    -0.58
    poke
    -0.57
    Fresh
    -0.57
     reperto
    -0.57
    POSITIVE LOGITS
     incidentally
    1.11
     according
    1.08
     unsurprisingly
    1.03
    according
    0.99
     interestingly
    0.98
     ironically
    0.98
     moreover
    0.96
     unlike
    0.93
     alas
    0.92
     fortunately
    0.91
    Activations Density 0.078%

    No Known Activations