© 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. 11-RES-JB
    11. 7113
    Prev
    Next
    INDEX
    Explanations

    references to autograph signing

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forth
    -0.71
    lihood
    -0.69
    nesday
    -0.64
     harness
    -0.63
     Penet
    -0.60
     VI
    -0.60
     Forbidden
    -0.58
     Continued
    -0.58
    imaru
    -0.56
     Sutton
    -0.56
    POSITIVE LOGITS
    ographs
    1.48
    opsy
    1.44
    ograph
    1.43
    umn
    1.42
    onomous
    1.42
    ographed
    1.34
    onomy
    1.32
    obi
    1.27
    ocom
    1.25
    ograp
    1.23
    Activations Density 0.024%

    No Known Activations