© 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. 14789
    Prev
    Next
    INDEX
    Explanations

    names and titles related to political figures and government positions

    oai_token-act-pair · gpt-3.5-turbo

    specific references to online or social media interactions

    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
    }.
    -0.71
    ".
    -0.66
    ?".
    -0.63
     };
    -0.62
    ''.
    -0.61
    SPONSORED
    -0.60
    .).
    -0.60
     });
    -0.60
    VIDIA
    -0.60
     ).
    -0.59
    POSITIVE LOGITS
     extensively
    0.69
     differently
    0.68
     squarely
    0.61
     aback
    0.60
    's
    0.59
     via
    0.59
     bandwagon
    0.58
     cautiously
    0.57
     separately
    0.57
     dilemma
    0.56
    Activations Density 1.000%

    No Known Activations