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. 1176
    Prev
    Next
    INDEX
    Explanations

    prepositions and articles that come before specific verbs

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating authorship, measurement, or timing in contexts related to observations or studies

    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
     mixer
    -0.71
     inclined
    -0.66
     sugars
    -0.65
     prospects
    -0.60
    bryce
    -0.59
    base
    -0.59
     collaborator
    -0.58
     wrapper
    -0.57
    natureconservancy
    -0.57
    ses
    -0.57
    POSITIVE LOGITS
    kinson
    0.73
    ammy
    0.72
     Alonso
    0.72
    ãĥ¯
    0.71
    ipel
    0.69
     Cosponsors
    0.65
    ropolitan
    0.65
    ushima
    0.64
    "]=>
    0.63
    raltar
    0.63
    Activations Density 0.417%

    No Known Activations