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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21248
    Prev
    Next
    INDEX
    Explanations

    keywords related to motion and movement

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "motion" and related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rosso
    -0.82
    scl
    -0.70
     sqor
    -0.68
    dds
    -0.66
    arding
    -0.65
    ilies
    -0.64
    allery
    -0.64
    regor
    -0.64
    soDeliveryDate
    -0.64
    aez
    -0.63
    POSITIVE LOGITS
     motion
    1.11
     Motion
    1.04
    motion
    1.03
    Motion
    0.99
     motions
    0.87
     sickness
    0.83
    immune
    0.79
     Picture
    0.78
    ucl
    0.76
    less
    0.75
    Activations Density 0.010%

    No Known Activations