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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5776
    Prev
    Next
    INDEX
    Explanations

    words related to rotation or movement

    oai_token-act-pair · gpt-3.5-turbo

    words related to rotation and movement

    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
    ortium
    -0.69
     Sug
    -0.66
    speech
    -0.64
    gotten
    -0.62
    ilies
    -0.62
    iaries
    -0.61
     Fathers
    -0.61
     adul
    -0.61
    Veter
    -0.60
    unts
    -0.58
    POSITIVE LOGITS
    cycles
    0.84
    axis
    0.77
     knob
    0.76
     gears
    0.74
    shaped
    0.73
     velocity
    0.73
    shape
    0.73
     inertia
    0.72
    direction
    0.71
     direction
    0.71
    Activations Density 0.097%

    No Known Activations