© 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. 10188
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to legal or authoritative contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to prevention or hindrance in various contexts

    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
    estyles
    -0.65
    soDeliveryDate
    -0.58
    arton
    -0.58
    entin
    -0.57
    rued
    -0.57
    ritten
    -0.56
    rote
    -0.56
    rette
    -0.56
    Rated
    -0.55
    hedon
    -0.54
    POSITIVE LOGITS
     from
    1.28
    from
    1.13
     FROM
    1.08
     accessing
    0.96
     From
    0.95
    From
    0.93
     harming
    0.87
     obtaining
    0.84
     gaining
    0.80
     slipping
    0.78
    Activations Density 0.128%

    No Known Activations