© 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. 4651
    Prev
    Next
    INDEX
    Explanations

    quotations within a text

    oai_token-act-pair · gpt-3.5-turbo

    quoted phrases or speech within the text

    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
     affiliate
    -0.76
     roar
    -0.73
     opener
    -0.73
     clen
    -0.72
     matter
    -0.72
     affair
    -0.72
     Vs
    -0.70
     reel
    -0.70
     shutter
    -0.69
     rall
    -0.69
    POSITIVE LOGITS
    significant
    1.49
    multiple
    1.44
    moderate
    1.40
    sever
    1.37
    reasonable
    1.36
    special
    1.34
    technical
    1.33
    Operation
    1.32
    extremely
    1.32
    extra
    1.31
    Activations Density 0.148%

    No Known Activations