© 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. 8-RES-JB
    11. 2697
    Prev
    Next
    INDEX
    Explanations

    phrases related to the jaw or actions involving the jaw

    oai_token-act-pair · gpt-3.5-turbo

    references to the jaw or actions related to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUM
    -0.68
    agents
    -0.68
     Ãī
    -0.67
    istant
    -0.67
     Galactic
    -0.66
    uve
    -0.65
     Holo
    -0.65
    markets
    -0.63
     Greene
    -0.61
     Edison
    -0.60
    POSITIVE LOGITS
    bone
    1.19
    bones
    1.18
    doms
    0.99
    Bone
    0.94
    dropping
    0.92
    breaker
    0.90
     clen
    0.84
    liners
    0.83
    keye
    0.83
    line
    0.83
    Activations Density 0.042%

    No Known Activations