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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 3462
    Prev
    Next
    INDEX
    Explanations

    technical terms or acronyms related to infrared (IR) technology

    oai_token-act-pair · gpt-3.5-turbo

    references to infrared (IR) technology and its applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xit
    -0.85
    ça
    -0.71
     Pound
    -0.66
    zzo
    -0.64
    amination
    -0.63
    ieri
    -0.63
    css
    -0.62
    gaard
    -0.61
     Archdemon
    -0.61
    yards
    -0.61
    POSITIVE LOGITS
    ROR
    1.04
    TY
    0.99
    WIN
    0.96
    CLE
    0.94
    LESS
    0.94
    FU
    0.93
    COLOR
    0.93
    WIND
    0.90
    LY
    0.86
    OME
    0.85
    Activations Density 0.012%

    No Known Activations