© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 7131
    Prev
    Next
    INDEX
    Explanations

    words related to technical specifications and scenarios

    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
     rage
    -0.62
     earthqu
    -0.61
     citiz
    -0.59
     eleph
    -0.56
     hurry
    -0.55
    manship
    -0.53
     precaution
    -0.53
     outraged
    -0.53
     myster
    -0.52
     fury
    -0.52
    POSITIVE LOGITS
    .,
    1.13
    .
    1.02
    .;
    0.99
    .:
    0.99
    pecially
    0.97
    .).
    0.96
    .),
    0.94
    .)
    0.91
    .):
    0.89
    -)
    0.88
    Activations Density 0.039%

    No Known Activations