© 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. 7094
    Prev
    Next
    INDEX
    Explanations

    mentions of people working or collaborating together

    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
    ichever
    -0.61
    odge
    -0.60
    "}],"
    -0.57
    agogue
    -0.57
    omed
    -0.56
     sterile
    -0.56
    Bind
    -0.56
    bestos
    -0.56
     pestic
    -0.56
    impact
    -0.55
    POSITIVE LOGITS
     tweeting
    1.14
     backstage
    1.10
    ðŁĺ
    1.01
     joking
    0.99
     ðŁĺ
    0.99
     (@
    0.95
     shortly
    0.95
     ðŁij
    0.94
     tonight
    0.94
     onstage
    0.94
    Activations Density 0.503%

    No Known Activations