© 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. 0-RES-JB
    6. 16919
    Prev
    Next
    INDEX
    Explanations

    verbs related to actively pursuing something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pursue" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ools
    -0.73
    Cond
    -0.68
     Relief
    -0.62
     +/-
    -0.62
     Sodium
    -0.62
    liness
    -0.61
     Ratings
    -0.61
     lol
    -0.61
     Rite
    -0.61
    unny
    -0.61
    POSITIVE LOGITS
     pursue
    3.08
     pursued
    2.82
     pursuing
    2.53
     pursuit
    2.14
     purs
    1.79
     pursuits
    1.64
     chase
    1.59
     pursu
    1.40
     Purs
    1.35
     chasing
    1.32
    Activations Density 0.014%

    No Known Activations