© 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. 6-RES-JB
    11. 11752
    Prev
    Next
    INDEX
    Explanations

    sentences emphasizing a specific point or conclusion

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce a pivotal statement or emphasize key points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oud
    -0.80
    onet
    -0.80
    alysed
    -0.79
    izons
    -0.77
    ema
    -0.75
    agon
    -0.75
    20439
    -0.72
    itol
    -0.69
    odox
    -0.68
     inspector
    -0.68
    POSITIVE LOGITS
     namely
    0.80
     Why
    0.78
     Tactics
    0.71
     Where
    0.71
     Bye
    0.70
     Who
    0.70
     What
    0.69
     Does
    0.67
     How
    0.66
     Will
    0.66
    Activations Density 0.132%

    No Known Activations