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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 1096
    Prev
    Next
    INDEX
    Explanations

    names of organizations or entities, such as "Fiat Chrysler Automobiles" and "Maryhill Winery Tasting Room"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of companies, places, and significant entities

    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
     piping
    -0.72
    anwhile
    -0.71
    gently
    -0.66
     faint
    -0.66
     sheer
    -0.65
    imately
    -0.64
    gered
    -0.63
    ³³³³³³³³³³³³³³³³
    -0.60
    arily
    -0.59
    successfully
    -0.59
    POSITIVE LOGITS
    Che
    0.74
    Ps
    0.70
    Pen
    0.67
     Highway
    0.66
     Street
    0.66
    World
    0.66
    Hack
    0.65
    Mos
    0.64
    Sal
    0.64
    Dun
    0.64
    Activations Density 0.389%

    No Known Activations