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. 552
    Prev
    Next
    INDEX
    Explanations

    various computer programming code snippets

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and functions related to programming and data processing

    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
    natureconservancy
    -0.79
    eas
    -0.70
    é¾įå
    -0.69
    én
    -0.69
    xus
    -0.69
     belts
    -0.67
    cutting
    -0.66
    ournal
    -0.66
    arag
    -0.64
     scrut
    -0.64
    POSITIVE LOGITS
    _
    1.10
    __
    0.92
    _-_
    0.86
    ()
    0.77
    ._
    0.72
    ___
    0.71
    _(
    0.65
     Anon
    0.64
    llor
    0.62
    []
    0.61
    Activations Density 0.086%

    No Known Activations