Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 20977
    Prev
    Next
    INDEX
    Explanations

    entities related to motorsports and technical organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific organizations, particularly in the context of motorsports and engineering

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

    No Comments

    Negative Logits
    ander
    -0.79
    andering
    -0.78
    anders
    -0.75
    ages
    -0.73
    ularity
    -0.71
    hots
    -0.70
    upt
    -0.70
    iah
    -0.68
    othy
    -0.66
    erville
    -0.66
    POSITIVE LOGITS
     FIA
    0.84
    DF
    0.82
     Formula
    0.76
    EGIN
    0.74
    senal
    0.74
    DEF
    0.73
     Parliament
    0.73
    ÃĽ
    0.72
     Tournament
    0.70
    escription
    0.66
    Activations Density 0.013%

    No Known Activations