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. 11-RES-JB
    6. 2927
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical and statistical concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to Bayesian statistics and probability distributions

    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
    advertising
    -0.91
    Medic
    -0.86
    Apps
    -0.85
    aws
    -0.80
    apps
    -0.78
    mails
    -0.78
    Dream
    -0.76
    leground
    -0.75
    Kid
    -0.75
    stories
    -0.75
    POSITIVE LOGITS
     radius
    1.40
     coefficient
    1.37
     exponent
    1.37
     velocity
    1.33
     angular
    1.29
     distance
    1.28
     inverse
    1.27
     slope
    1.26
     coefficients
    1.25
     amplitude
    1.24
    Activations Density 0.220%

    No Known Activations