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. 0-RES-JB
    6. 19642
    Prev
    Next
    INDEX
    Explanations

    statements related to various types of modeling processes, specifically related to statistical modeling, spatial modeling, 3D modeling, and simulation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to data modeling and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inous
    -0.76
    士
    -0.76
     Shutdown
    -0.73
     Oath
    -0.71
     offence
    -0.68
     Extra
    -0.66
    ãĤ¯
    -0.64
     Charges
    -0.64
     Constitution
    -0.64
     Offensive
    -0.64
    POSITIVE LOGITS
     modeling
    3.57
     modelling
    3.11
     mapping
    1.63
     designing
    1.54
     modeled
    1.51
     forecasting
    1.44
     estimating
    1.36
     sculpt
    1.33
     posing
    1.33
     photograp
    1.27
    Activations Density 0.044%

    No Known Activations