Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 21752
    Prev
    Next
    INDEX
    Explanations

    mentions of bonuses or rewards

    oai_token-act-pair · gpt-3.5-turbo

    mentions of bonuses or rewards

    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
    tics
    -0.86
    scape
    -0.80
    ãĤ¢ãĥ«
    -0.78
    URES
    -0.78
    atters
    -0.77
    tic
    -0.74
    lé
    -0.74
    turn
    -0.72
    ichen
    -0.71
    ŀ
    -0.71
    POSITIVE LOGITS
     bonus
    1.21
     bonuses
    1.08
     depreciation
    0.95
     accrued
    0.84
     Bonus
    0.81
     indemn
    0.81
     extras
    0.79
    Bonus
    0.78
     parachute
    0.77
     accol
    0.76
    Activations Density 0.015%

    No Known Activations