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. 1674
    Prev
    Next
    INDEX
    Explanations

    phrases related to thorough investigation or detailed examination

    oai_token-act-pair · gpt-3.5-turbo

    the word "extensive" and its varying forms, indicating emphasis on thoroughness or comprehensiveness

    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
    opers
    -0.64
    CP
    -0.63
    Earth
    -0.63
     Alive
    -0.63
    Frames
    -0.63
     Tycoon
    -0.63
    Anderson
    -0.61
    Young
    -0.61
    nery
    -0.61
    atu
    -0.61
    POSITIVE LOGITS
     amounts
    0.99
    mble
    0.88
     portions
    0.78
     quantities
    0.77
     thorough
    0.76
     extensive
    0.76
     disadvantages
    0.75
    eatures
    0.75
    ãĤ£
    0.75
     multimedia
    0.70
    Activations Density 0.010%

    No Known Activations