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

    Neuronpedia

    Jacobian LensNEW
    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. 16584
    Prev
    Next
    INDEX
    Explanations

    numbers related to financial figures or funding allocations

    oai_token-act-pair · gpt-3.5-turbo

    monetary amounts and allocations in funding contexts

    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
     haunt
    -0.73
     struggles
    -0.68
    ife
    -0.67
     haun
    -0.67
    famous
    -0.66
     Errors
    -0.66
     collide
    -0.66
    beard
    -0.64
     disappearance
    -0.63
     sweaty
    -0.62
    POSITIVE LOGITS
     concess
    1.11
     grants
    1.06
     allocated
    1.01
     funding
    1.00
     Funds
    1.00
     grant
    0.95
     funds
    0.93
     allocations
    0.92
     scholarships
    0.92
     Funding
    0.91
    Activations Density 0.255%

    No Known Activations