© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 17931
    Prev
    Next
    INDEX
    Explanations

    sentences concluding a point or with a strong emphasis

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express finality or conclusions

    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
    itled
    -0.67
    ancy
    -0.64
    atorium
    -0.62
    marked
    -0.61
    aband
    -0.60
    aditional
    -0.59
     replacing
    -0.59
     assignment
    -0.59
     first
    -0.58
     phased
    -0.58
    POSITIVE LOGITS
     Lastly
    1.42
    etc
    1.38
     Finally
    1.27
    Lastly
    1.10
    Finally
    1.06
     etc
    1.03
     Whatever
    0.98
    These
    0.93
    whatever
    0.89
     These
    0.89
    Activations Density 0.790%

    No Known Activations