© 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. 16444
    Prev
    Next
    INDEX
    Explanations

    specific words related to reasons or causes

    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
     rolling
    -0.68
     in
    -0.65
    ,
    -0.65
     or
    -0.62
     and
    -0.62
     heavily
    -0.62
     management
    -0.62
     shaped
    -0.61
     mixed
    -0.61
     Media
    -0.60
    POSITIVE LOGITS
    because
    1.97
    until
    1.93
    when
    1.91
    without
    1.87
    instead
    1.86
    against
    1.85
    along
    1.82
    during
    1.76
    unless
    1.76
    among
    1.73
    Activations Density 0.036%

    No Known Activations