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. 8-RES-JB
    6. 20704
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to research projects and government initiatives

    oai_token-act-pair · gpt-3.5-turbo

    terms related to assessments, studies, and structured systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pawn
    -0.80
     recl
    -0.73
     queen
    -0.73
    depending
    -0.72
    animal
    -0.71
    ĻĤ
    -0.71
    axter
    -0.70
     err
    -0.69
     racer
    -0.69
     skiing
    -0.68
    POSITIVE LOGITS
     Initiative
    1.19
     Programme
    1.14
     Project
    1.11
     Program
    1.08
     Fund
    1.08
     Agreement
    1.07
     Committee
    1.06
     Suite
    1.05
     Experiment
    1.05
     Collection
    1.03
    Activations Density 0.236%

    No Known Activations