© 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. 10-RES-JB
    11. 4334
    Prev
    Next
    INDEX
    Explanations

    articles or pieces of writing inviting the reader to learn more about a topic

    oai_token-act-pair · gpt-3.5-turbo

    instances of text where specific topics or issues are discussed

    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
    ,)
    -0.76
    tml
    -0.76
     princ
    -0.75
     newsp
    -0.67
     desper
    -0.66
    itta
    -0.64
     paran
    -0.63
     Deity
    -0.63
     utilized
    -0.63
     citiz
    -0.62
    POSITIVE LOGITS
    ]).
    0.81
    %]
    0.81
    Facebook
    0.76
     ÂŃ
    0.73
     ];
    0.71
    mone
    0.67
     ï
    0.65
    ]);
    0.64
    ].
    0.63
    ³³³³³³³³
    0.63
    Activations Density 0.020%

    No Known Activations