© 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. 7-RES-JB
    11. 18787
    Prev
    Next
    INDEX
    Explanations

    terms related to Formula racing

    oai_token-act-pair · gpt-3.5-turbo

    references to "Formula" followed by a number, indicating a focus on motorsport terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asking
    -0.78
    orah
    -0.72
    essage
    -0.71
    ocker
    -0.70
    asio
    -0.69
     WARN
    -0.68
    ym
    -0.68
    frames
    -0.67
    dim
    -0.65
    itent
    -0.65
    POSITIVE LOGITS
    ĩ
    0.89
     Drift
    0.86
    ĺ
    0.86
    ī
    0.84
    ĭ
    0.76
     XIV
    0.75
    ĥ
    0.71
    ij
    0.70
    IJ
    0.69
     Renault
    0.68
    Activations Density 0.043%

    No Known Activations