© 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. 2-RES-JB
    11. 4494
    Prev
    Next
    INDEX
    Explanations

    references to public events or activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "demonstration" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saline
    -0.82
    laus
    -0.73
    oho
    -0.73
    esthetic
    -0.64
    olly
    -0.63
    chance
    -0.62
    abol
    -0.62
    missions
    -0.61
    omer
    -0.60
    pop
    -0.60
    POSITIVE LOGITS
     demonstration
    1.09
     demonstrations
    0.91
     GOODMAN
    0.80
     demonstrating
    0.77
     demonstrators
    0.77
    arily
    0.73
    stration
    0.72
     ank
    0.71
    wcsstore
    0.71
     glim
    0.71
    Activations Density 0.012%

    No Known Activations