© 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. 10-RES-JB
    11. 6103
    Prev
    Next
    INDEX
    Explanations

    phrases related to future events or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey finality or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quir
    -0.77
     gou
    -0.75
     bonded
    -0.72
     challeng
    -0.72
     downed
    -0.71
     aven
    -0.70
     clos
    -0.70
     groove
    -0.68
     volunte
    -0.68
     looted
    -0.68
    POSITIVE LOGITS
     However
    1.79
    However
    1.59
     But
    1.56
     Unfortunately
    1.54
    But
    1.39
     Yet
    1.38
     Others
    1.34
     Alas
    1.34
     Wrong
    1.32
    BUT
    1.29
    Activations Density 0.575%

    No Known Activations