© 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. 16474
    Prev
    Next
    INDEX
    Explanations

    keywords related to operational procedures and technology practices

    oai_token-act-pair · gpt-3.5-turbo
    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
     waiver
    -0.69
     carn
    -0.68
     retaining
    -0.67
     immersion
    -0.66
     mention
    -0.66
     moisture
    -0.65
     reference
    -0.64
     knowing
    -0.64
     lingu
    -0.64
     scenarios
    -0.62
    POSITIVE LOGITS
    Op
    4.30
     Op
    2.29
     op
    1.64
    Ops
    1.54
    op
    1.46
    OP
    1.33
    Oper
    1.21
    Operation
    1.13
    Pan
    1.09
     ops
    1.08
    Activations Density 0.011%

    No Known Activations