© 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. 5182
    Prev
    Next
    INDEX
    Explanations

    proper names, especially the name "Kurt"

    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
    hare
    -0.76
    tower
    -0.69
    cale
    -0.66
    atories
    -0.65
    atics
    -0.64
    士
    -0.63
    orthy
    -0.62
     rigging
    -0.62
    SHARE
    -0.62
    hip
    -0.62
    POSITIVE LOGITS
    zman
    1.27
    osis
    1.04
    tering
    0.97
     Angle
    0.95
     Von
    0.95
     Ops
    0.87
    inous
    0.86
    iev
    0.86
    ting
    0.84
    imens
    0.80
    Activations Density 0.053%

    No Known Activations