© 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. 8-RES-JB
    11. 6921
    Prev
    Next
    INDEX
    Explanations

    information about monetary rewards and funding

    oai_token-act-pair · gpt-3.5-turbo

    monetary rewards and funding related to various initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ife
    -0.75
     dominating
    -0.71
    ovies
    -0.68
    edIn
    -0.68
    inventoryQuantity
    -0.68
    Commerce
    -0.67
    arenthood
    -0.65
    ettings
    -0.65
     Occupations
    -0.65
    ulence
    -0.64
    POSITIVE LOGITS
     concess
    0.97
    -$
    0.89
     incentive
    0.89
     (£
    0.86
     rebate
    0.84
     Reward
    0.83
     scholarships
    0.82
    ESA
    0.82
     apiece
    0.80
     stip
    0.79
    Activations Density 0.228%

    No Known Activations