© 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. 11-RES-JB
    11. 7458
    Prev
    Next
    INDEX
    Explanations

    quotations within double quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks and related punctuation in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tabloid
    -0.91
     viral
    -0.89
     SB
    -0.87
     ADS
    -0.86
     HB
    -0.84
     RG
    -0.84
     tech
    -0.83
     BS
    -0.83
     GS
    -0.82
     CPS
    -0.82
    POSITIVE LOGITS
    Whoever
    1.52
    Peace
    1.43
    Father
    1.43
    Thus
    1.42
    Where
    1.42
    Against
    1.40
    Who
    1.38
    Through
    1.38
    Faith
    1.37
    Lord
    1.37
    Activations Density 0.237%

    No Known Activations