© 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. 9-RES-JB
    11. 2467
    Prev
    Next
    INDEX
    Explanations

    statements indicating truth, accuracy, or correctness

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avascript
    -0.66
    Fish
    -0.64
    KEN
    -0.64
    ãĥķ
    -0.63
    "],
    -0.62
    LESS
    -0.61
    Afee
    -0.60
    çīĪ
    -0.60
    Ãį
    -0.57
    icular
    -0.57
    POSITIVE LOGITS
     indeed
    1.04
     ever
    0.89
     successful
    0.82
     somehow
    0.79
     someday
    0.76
     anything
    0.75
     truly
    0.74
     accurate
    0.73
     correct
    0.71
     true
    0.71
    Activations Density 0.192%

    No Known Activations