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. 3-RES-JB
    6. 22072
    Prev
    Next
    INDEX
    Explanations

    mentions of time periods, specifically focusing on the early stages of development or history

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "early."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    retched
    -0.78
    edIn
    -0.77
    ourge
    -0.75
    mbuds
    -0.74
    unity
    -0.71
    laws
    -0.70
    ittee
    -0.68
    olulu
    -0.67
    atism
    -0.67
    dain
    -0.66
    POSITIVE LOGITS
     adop
    0.84
     stages
    0.83
     phases
    0.81
     drafts
    0.78
     childhood
    0.73
     onset
    0.72
    prototype
    0.72
     twenties
    0.72
    -'
    0.70
    ummer
    0.69
    Activations Density 0.025%

    No Known Activations