© 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. 15282
    Prev
    Next
    INDEX
    Explanations

    verbs related to sudden action or decision

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "jump" or variations of it

    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
    ãĥĨãĤ£
    -0.69
    minus
    -0.68
    $$$$
    -0.68
    gem
    -0.65
    ifice
    -0.64
     è£ı
    -0.64
     Ain
    -0.62
     Smile
    -0.61
    eq
    -0.61
    代
    -0.61
    POSITIVE LOGITS
    frog
    0.92
    uits
    0.87
    olicy
    0.83
    uit
    0.83
    fleet
    0.83
    ulic
    0.78
     jump
    0.77
    olean
    0.77
    oons
    0.76
    rill
    0.74
    Activations Density 0.019%

    No Known Activations