© 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. 6044
    Prev
    Next
    INDEX
    Explanations

    words related to providing financial support or resources

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial support or funding

    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
    endant
    -0.74
    olit
    -0.73
    mare
    -0.73
    empt
    -0.66
    place
    -0.66
    ldom
    -0.66
    æ³
    -0.65
    ique
    -0.65
     sidx
    -0.65
    oland
    -0.64
    POSITIVE LOGITS
     scholarships
    0.86
     upkeep
    0.81
     projects
    0.80
     research
    0.78
    ament
    0.74
     charities
    0.73
     extras
    0.73
     Expend
    0.71
     abortions
    0.71
     fundraising
    0.69
    Activations Density 0.084%

    No Known Activations