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. 9995
    Prev
    Next
    INDEX
    Explanations

    words related to combinations or matches

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pair" and its variations indicating combinations or associations

    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
    icz
    -0.80
    raq
    -0.78
    DW
    -0.73
    cott
    -0.68
    hene
    -0.67
    IVER
    -0.64
    bern
    -0.64
    metic
    -0.64
    den
    -0.63
    ARDS
    -0.63
    POSITIVE LOGITS
     pairs
    0.99
     pair
    0.88
     pairing
    0.86
     paired
    0.86
     Pair
    0.83
    onym
    0.74
     mates
    0.72
     seamlessly
    0.71
     between
    0.70
     partner
    0.67
    Activations Density 0.025%

    No Known Activations