© 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. 1286
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ngth
    -0.82
    secondary
    -0.81
    ĨĴ
    -0.79
    BIL
    -0.71
     newcom
    -0.68
    @#&
    -0.68
    milo
    -0.68
    íķ
    -0.66
    oras
    -0.64
    rl
    -0.64
    POSITIVE LOGITS
     Cuomo
    0.78
    ideo
    0.69
    ity
    0.68
     lust
    0.66
     Sonia
    0.65
     Strauss
    0.62
     Shinji
    0.62
     Nicarag
    0.62
     Spect
    0.62
     spect
    0.62
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.