© 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. 4-RES-JB
    11. 15354
    Prev
    Next
    INDEX
    Explanations

    terms related to physical actions involving cranking or turning a lever

    oai_token-act-pair · gpt-3.5-turbo

    words related to mechanical actions or movements involving cranking

    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
     Hers
    -0.72
    pha
    -0.69
     Niet
    -0.69
    tnc
    -0.68
     IMAGES
    -0.66
     Lich
    -0.65
     Guardians
    -0.64
     Austral
    -0.64
     bloom
    -0.62
    endi
    -0.61
    POSITIVE LOGITS
     crank
    1.13
    cases
    0.85
     horsepower
    0.83
    bike
    0.80
    case
    0.80
    oly
    0.79
    chairs
    0.78
     rod
    0.75
    loader
    0.75
    ular
    0.75
    Activations Density 0.029%

    No Known Activations