© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 12228
    Prev
    Next
    INDEX
    Explanations

    phrases related to restrictions or limitations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to restrictions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MORE
    -0.72
    CHA
    -0.70
    ingly
    -0.69
    ))))
    -0.69
    natureconservancy
    -0.66
    });
    -0.64
    dl
    -0.64
     syndrome
    -0.63
    ris
    -0.62
    itance
    -0.62
    POSITIVE LOGITS
     certain
    0.82
     those
    0.78
     narrow
    0.68
     limited
    0.68
     finite
    0.67
     cater
    0.67
     accommodate
    0.66
     specific
    0.65
     subsistence
    0.65
     continental
    0.64
    Activations Density 0.148%

    No Known Activations