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. 1-RES-JB
    6. 9133
    Prev
    Next
    INDEX
    Explanations

    references to specific technical instructions or details

    oai_token-act-pair · gpt-3.5-turbo

    references to the Fedora operating system and terms related to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    essor
    -0.91
    mond
    -0.85
    clair
    -0.84
    illac
    -0.83
    erd
    -0.82
    str
    -0.82
    imony
    -0.76
    mia
    -0.75
    ements
    -0.75
    itaire
    -0.75
    POSITIVE LOGITS
    200000
    0.79
     Kelvin
    0.78
     Helsinki
    0.75
     Polo
    0.74
     srf
    0.71
     Belfast
    0.67
    orthy
    0.67
     Shogun
    0.66
     Celsius
    0.64
     Fahrenheit
    0.63
    Activations Density 0.028%

    No Known Activations