© 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. 10-RES-JB
    11. 8558
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a list of items or considerations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the enumeration or listing of items or concepts

    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
    Ire
    -0.74
    ebook
    -0.70
    ergy
    -0.65
    endars
    -0.57
    enne
    -0.57
    psc
    -0.56
     Andromeda
    -0.56
    Beast
    -0.55
    aukee
    -0.55
    olini
    -0.55
    POSITIVE LOGITS
    :-
    1.27
    %:
    1.15
    :
    1.04
     viz
    1.00
    :(
    0.99
    :#
    0.94
    :'
    0.92
    :"
    0.90
    *:
    0.89
    ':
    0.89
    Activations Density 0.140%

    No Known Activations