© 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. 11-RES-JB
    11. 23747
    Prev
    Next
    INDEX
    Explanations

    references to social media platforms and online activities

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and conjunctions that indicate connection or continuation in thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ledged
    -0.80
    olitics
    -0.77
    ISE
    -0.71
    ailand
    -0.67
    ãĥ¤
    -0.65
    brates
    -0.65
    urse
    -0.64
    prise
    -0.63
    ?????-
    -0.62
    ursed
    -0.62
    POSITIVE LOGITS
     distributing
    1.42
     exchanging
    1.41
     installing
    1.41
     arranging
    1.41
     repairing
    1.39
     constructing
    1.39
     modifying
    1.39
     manipulating
    1.39
     converting
    1.39
     submitting
    1.38
    Activations Density 0.209%

    No Known Activations