© 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. 3701
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical actions involving movement toward a specific direction

    oai_token-act-pair · gpt-3.5-turbo

    the word "to" and its various contexts and usages

    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
    icipated
    -0.72
    hops
    -0.71
    reports
    -0.71
    artisan
    -0.68
     vows
    -0.68
    ecided
    -0.65
    nces
    -0.65
     prosecutions
    -0.65
     Photographer
    -0.65
    pie
    -0.65
    POSITIVE LOGITS
    pload
    1.05
     maximize
    1.02
     minimize
    1.02
    ilet
    1.02
     relieve
    1.01
     conserve
    0.97
     regain
    0.96
     celebrate
    0.95
    pless
    0.95
     commemorate
    0.95
    Activations Density 0.405%

    No Known Activations