© 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. 10-RES-JB
    6. 6668
    Prev
    Next
    INDEX
    Explanations

    actions involving movement and physical interactions

    oai_token-act-pair · gpt-3.5-turbo

    verbs or actions related to physical movements or interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å§«
    -0.65
     Growth
    -0.60
     Lauder
    -0.60
     Millennium
    -0.60
    GROUND
    -0.60
    MENT
    -0.59
    MENTS
    -0.58
     VAL
    -0.58
     female
    -0.57
     medieval
    -0.56
    POSITIVE LOGITS
    owed
    1.20
    uked
    1.10
    rolled
    1.08
    atted
    1.07
    ucked
    1.07
    rawled
    1.05
    umped
    1.03
    aped
    1.00
    itched
    1.00
    umbered
    0.99
    Activations Density 0.073%

    No Known Activations