© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 12-RES-JB
    6. 2647
    Prev
    Next
    INDEX
    Explanations

    names of fictional characters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    key characters, factors, and elements related to specific narrative contexts and political discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pires
    -0.46
     gifted
    -0.44
    wrote
    -0.44
     decorated
    -0.42
     translated
    -0.42
     shines
    -0.41
     painstaking
    -0.41
     changed
    -0.41
     bilingual
    -0.41
     undeniably
    -0.41
    POSITIVE LOGITS
    )?
    1.07
     ):
    0.96
     .)
    0.91
     );
    0.91
    "?
    0.91
    ],"
    0.89
    ?",
    0.89
     ];
    0.88
    .?
    0.87
     ])
    0.86
    Activations Density 1.396%

    No Known Activations