© 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
    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. 6635
    Prev
    Next
    INDEX
    Explanations

    words related to movement or physical motion

    oai_token-act-pair · gpt-3.5-turbo

    terms related to movement and dynamics

    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
    rosso
    -0.80
    scl
    -0.75
     sqor
    -0.72
    allery
    -0.67
    arding
    -0.67
    racuse
    -0.66
    ilies
    -0.66
    oys
    -0.64
    dds
    -0.64
    ythm
    -0.63
    POSITIVE LOGITS
     motion
    1.17
     Motion
    1.06
    motion
    1.06
    Motion
    1.02
     sickness
    0.89
     motions
    0.86
    immune
    0.83
    Animation
    0.80
    ucl
    0.77
     blur
    0.73
    Activations Density 0.009%

    No Known Activations