© 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. 2-RES-JB
    11. 9432
    Prev
    Next
    INDEX
    Explanations

    physical actions or movements

    oai_token-act-pair · gpt-3.5-turbo

    actions related to physical movements and precision in tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    taboola
    -0.73
     Flavoring
    -0.72
     Serving
    -0.66
    ONSORED
    -0.65
    gow
    -0.65
    financial
    -0.64
     Tumblr
    -0.63
     hospitality
    -0.63
     Pension
    -0.62
    Synopsis
    -0.62
    POSITIVE LOGITS
     glide
    0.92
     sideways
    0.81
     horizont
    0.78
     wob
    0.77
     axis
    0.76
    stro
    0.75
     collided
    0.75
     downwards
    0.74
     drift
    0.73
     velocity
    0.71
    Activations Density 0.885%

    No Known Activations