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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 4292
    Prev
    Next
    INDEX
    Explanations

    references to medical treatments or procedures involving IV (intravenous) therapy

    oai_token-act-pair · gpt-3.5-turbo

    references to intravenous (IV) treatments and related medical procedures

    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
    •GPT2 L5 Resid: RRLRRRRRRRRRRLRRRLLRRRRRRLL

    No Comments

    Negative Logits
     palms
    -0.77
    boards
    -0.76
    Else
    -0.76
     Fiorina
    -0.71
    geist
    -0.69
    chant
    -0.69
    lands
    -0.67
    âĸ¬
    -0.67
    board
    -0.66
    é¾įå¥ij士
    -0.66
    POSITIVE LOGITS
    ISION
    1.00
    III
    0.95
    IV
    0.89
    iolet
    0.81
    II
    0.80
    annis
    0.80
    erto
    0.79
    ANA
    0.79
    ENTS
    0.77
    itals
    0.77
    Activations Density 0.008%

    No Known Activations