Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 6526
    Prev
    Next
    INDEX
    Explanations

    words related to technology or computer programming

    oai_token-act-pair · gpt-3.5-turbo

    references to specific numerical values and identifiers

    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
     unpop
    -0.76
     ensu
    -0.62
     tyr
    -0.59
    unin
    -0.59
     Trin
    -0.56
     cryptoc
    -0.56
     experien
    -0.56
     themed
    -0.55
     ESC
    -0.54
     perspect
    -0.54
    POSITIVE LOGITS
    ;
    1.87
    .;
    1.74
    ";
    1.63
    ';
    1.62
    ;"
    1.60
    ;}
    1.56
    %;
    1.51
    );
    1.46
    ];
    1.44
     ;
    1.37
    Activations Density 0.180%

    No Known Activations