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. 13480
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a conclusion or final thought

    oai_token-act-pair · gpt-3.5-turbo

    conclusive statements or summaries at the end of paragraphs

    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
    mong
    -0.66
    dec
    -0.62
    ocl
    -0.60
    ga
    -0.58
    ung
    -0.57
    lis
    -0.57
    folk
    -0.56
    lands
    -0.56
    anim
    -0.56
    umerable
    -0.56
    POSITIVE LOGITS
    icia
    0.84
     reunited
    0.78
    hiba
    0.72
    icates
    0.69
    elvet
    0.69
    oner
    0.67
     CoC
    0.65
    aire
    0.65
    icating
    0.64
     conclud
    0.64
    Activations Density 0.021%

    No Known Activations