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. 4-RES-JB
    6. 15082
    Prev
    Next
    INDEX
    Explanations

    special characters or code snippets with specific patterns

    oai_token-act-pair · gpt-3.5-turbo

    code snippets or programming-related elements

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

    No Comments

    Negative Logits
    ĸļ
    -0.92
     mathemat
    -0.74
     paran
    -0.71
     Sau
    -0.70
     toile
    -0.70
     ambassadors
    -0.68
     puberty
    -0.67
    hement
    -0.67
    terday
    -0.66
     Manit
    -0.66
    POSITIVE LOGITS
    };
    1.27
    """
    1.07
    Output
    1.05
    */
    1.04
    ERROR
    0.96
    &&
    0.96
    ================
    0.95
    @@
    0.94
    Definition
    0.94
    /*
    0.94
    Activations Density 0.120%

    No Known Activations