© 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. 4-RES-JB
    11. 2849
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the word "document" in text

    oai_token-act-pair · gpt-3.5-turbo

    references to specific documents

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

    No Comments

    Negative Logits
    NetMessage
    -0.80
    cffff
    -0.79
    Stars
    -0.76
    luster
    -0.76
    akening
    -0.76
    avorite
    -0.74
    bye
    -0.73
    olean
    -0.70
     Flavoring
    -0.68
    bid
    -0.68
    POSITIVE LOGITS
    arians
    1.12
    arian
    1.08
    ually
    1.01
     document
    0.93
    aries
    0.80
     documents
    0.79
    document
    0.76
    abal
    0.76
    uments
    0.76
    ably
    0.75
    Activations Density 0.016%

    No Known Activations