© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 3050
    Prev
    Next
    INDEX
    Explanations

    phrases related to bonuses or rewards

    oai_token-act-pair · gpt-3.5-turbo

    references to bonuses and rewards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apest
    -0.80
    ãĤ¢ãĥ«
    -0.78
    flies
    -0.74
    lé
    -0.73
    alter
    -0.73
    tics
    -0.71
    Ö¼
    -0.70
    scape
    -0.69
    turn
    -0.68
    phis
    -0.67
    POSITIVE LOGITS
     bonus
    0.98
     compartment
    0.80
     tiers
    0.79
     payout
    0.78
    vertisement
    0.78
     depreciation
    0.75
    vana
    0.74
    Reviewer
    0.74
     bonuses
    0.74
     extras
    0.74
    Activations Density 0.044%

    No Known Activations