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. 10325
    Prev
    Next
    INDEX
    Explanations

    examples of instances where phrases like "case study," "subject matter," and "story" are used

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "case study" and related expressions in various contexts

    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
    skill
    -0.76
    space
    -0.74
    draft
    -0.67
    NL
    -0.67
    Pres
    -0.67
    Rail
    -0.66
    Disc
    -0.65
    stream
    -0.65
    AppData
    -0.65
    cash
    -0.63
    POSITIVE LOGITS
    eer
    0.80
    eers
    0.69
     subtitle
    0.64
     sequel
    0.63
    ciation
    0.63
     Korra
    0.62
     supervisors
    0.62
    matically
    0.62
     fiasco
    0.61
     replay
    0.61
    Activations Density 0.356%

    No Known Activations