© 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. 4-RES-JB
    11. 6799
    Prev
    Next
    INDEX
    Explanations

    terms related to drawing or reaching conclusions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to conclusions or decision-making processes

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

    No Comments

    Negative Logits
    unte
    -0.65
    amen
    -0.65
     nurs
    -0.65
    abb
    -0.65
     booked
    -0.63
     talents
    -0.62
    drops
    -0.62
    eye
    -0.62
    bid
    -0.61
    gm
    -0.61
    POSITIVE LOGITS
     conclusion
    1.00
     conclusions
    0.92
    20439
    0.80
     Conclusion
    0.79
    éĸ
    0.73
    iveness
    0.68
    naire
    0.67
    essim
    0.67
    olicy
    0.65
    answer
    0.65
    Activations Density 0.012%

    No Known Activations