© 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. 1-RES-JB
    11. 24189
    Prev
    Next
    INDEX
    Explanations

    dates, locations, and proper nouns related to educational institutions and events

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.45
     Planes
    -0.43
     FANTASY
    -0.41
    AUT
    -0.39
     AST
    -0.39
     Hubble
    -0.38
    minist
    -0.38
    uzzle
    -0.38
     DRAG
    -0.38
     Continuous
    -0.38
    POSITIVE LOGITS
    zona
    0.47
    iola
    0.40
    allery
    0.40
     promot
    0.39
    ucci
    0.38
    ĸļ
    0.38
    interstitial
    0.38
    amara
    0.37
    ãĥ¼ãĥĨ
    0.37
    antes
    0.36
    Activations Density 10.827%

    No Known Activations