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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 9597
    Prev
    Next
    INDEX
    Explanations

    HTML/CSS syntax related text

    oai_token-act-pair · gpt-3.5-turbo

    semicolons and other punctuation marks used in coding or markup syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     trou
    -0.75
    bies
    -0.73
    vals
    -0.62
     fortun
    -0.62
     outraged
    -0.62
    bledon
    -0.60
     counselors
    -0.60
     resil
    -0.60
    ovy
    -0.60
    phia
    -0.58
    POSITIVE LOGITS
    -)
    1.04
    alias
    0.98
     /*
    0.92
     };
    0.89
     /**
    0.86
     //
    0.81
     ///
    0.76
     }
    0.76
    cloneembedreportprint
    0.75
    DW
    0.74
    Activations Density 0.034%

    No Known Activations