© 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. 3-RES-JB
    6. 13338
    Prev
    Next
    INDEX
    Explanations

    actions involving forceful or vigorous movements, such as 'stomping', 'strutting', 'blistering', or 'dunking'

    oai_token-act-pair · gpt-3.5-turbo

    action verbs related to physical movements or gestures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conflic
    -0.74
    artifacts
    -0.70
    merga
    -0.69
    cius
    -0.68
    externalActionCode
    -0.67
    ________________________
    -0.66
     millenn
    -0.66
     appropriation
    -0.65
    ĻĤ
    -0.64
    visual
    -0.63
    POSITIVE LOGITS
    ing
    1.28
    ed
    1.03
     stomp
    0.96
    boxing
    0.77
     isEnabled
    0.75
    sonian
    0.73
    eting
    0.72
    chairs
    0.70
     flap
    0.69
    doms
    0.69
    Activations Density 0.012%

    No Known Activations