© 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. 7-RES-JB
    11. 20808
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes

    oai_token-act-pair · gpt-3.5-turbo

    various forms of quotation marks and related punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gaard
    -0.72
    ometimes
    -0.69
    mosp
    -0.64
    nas
    -0.64
    etheless
    -0.64
    mens
    -0.63
    entimes
    -0.63
    tin
    -0.62
    ĻĤ
    -0.62
    MENTS
    -0.62
    POSITIVE LOGITS
     />
    1.03
    /"
    0.97
     %%
    0.84
     parsed
    0.80
     ++
    0.78
     );
    0.76
     redirect
    0.74
     });
    0.73
     alias
    0.72
     ||
    0.71
    Activations Density 0.054%

    No Known Activations