© 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. 0-RES-JB
    11. 16412
    Prev
    Next
    INDEX
    Explanations

    labels or titles within a structured document or webpage

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tennis
    -0.72
     Fusion
    -0.69
     tennis
    -0.68
     clan
    -0.68
     Crimson
    -0.67
     jet
    -0.66
     Cyber
    -0.65
     jets
    -0.64
     cra
    -0.64
     upgrade
    -0.62
    POSITIVE LOGITS
    Label
    3.08
    label
    2.66
    title
    1.42
    Title
    1.20
     Label
    1.19
    ppelin
    1.14
    Button
    1.10
    Text
    1.08
    lab
    1.07
    displayText
    0.97
    Activations Density 0.031%

    No Known Activations