© 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. 9-RES-JB
    11. 18418
    Prev
    Next
    INDEX
    Explanations

    items related to gratitude and rewards

    oai_token-act-pair · gpt-3.5-turbo

    elements related to appreciation and rewards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sects
    -0.75
     Occupations
    -0.74
    brids
    -0.73
     lows
    -0.73
     abuses
    -0.72
     highways
    -0.72
     Churches
    -0.72
    renches
    -0.71
     avenues
    -0.71
    axies
    -0.70
    POSITIVE LOGITS
     voucher
    0.98
     certificate
    0.94
     token
    0.91
     reminder
    0.90
     entit
    0.90
    card
    0.87
     identifier
    0.85
     coupon
    0.85
     badge
    0.84
     receipt
    0.83
    Activations Density 0.442%

    No Known Activations