© 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. 10-RES-JB
    11. 20452
    Prev
    Next
    INDEX
    Explanations

    phrases related to donations and the distribution of profits

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to financial proceeds and donations

    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
    thodox
    -0.71
    odox
    -0.67
     diction
    -0.67
    uden
    -0.66
    ready
    -0.63
    iery
    -0.63
     readiness
    -0.62
    rast
    -0.61
    paio
    -0.60
    zai
    -0.60
    POSITIVE LOGITS
     proceeds
    1.44
     donated
    1.34
     profits
    1.24
     royalties
    1.21
     deposited
    1.16
     earned
    1.15
     redistributed
    1.12
     earnings
    1.10
     Proceed
    1.06
     revenues
    1.06
    Activations Density 0.229%

    No Known Activations