© 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. 9-RES-JB
    11. 16068
    Prev
    Next
    INDEX
    Explanations

    terms related to formal suggestions or ideas for consideration

    oai_token-act-pair · gpt-3.5-turbo

    references to proposals or suggested plans

    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
    vin
    -0.78
    wan
    -0.69
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.67
    umi
    -0.66
    cott
    -0.66
    nie
    -0.66
    race
    -0.65
    oyal
    -0.65
    san
    -0.65
    zona
    -0.64
    POSITIVE LOGITS
     proposals
    0.99
     proposing
    0.89
     proposal
    0.87
     proposed
    0.76
     proposes
    0.75
     submitted
    0.72
     aimed
    0.71
     floated
    0.70
     unanimously
    0.70
     legalizing
    0.69
    Activations Density 0.063%

    No Known Activations