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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 8554
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific entity named "Aggie" or "Aggieland"

    oai_token-act-pair · gpt-3.5-turbo

    references to Aggies, the name of a sports team or group associated with a particular institution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atonin
    -0.74
    translation
    -0.72
     customs
    -0.70
    yright
    -0.69
     shutter
    -0.67
     bake
    -0.67
    CHAT
    -0.66
     prol
    -0.66
    henko
    -0.65
     plum
    -0.65
    POSITIVE LOGITS
     Agg
    3.99
    Agg
    2.63
     agg
    1.44
    agg
    1.39
     Longh
    1.24
     Ung
    1.13
     Buff
    1.10
     Territ
    1.03
     aggro
    1.00
     Ag
    1.00
    Activations Density 0.030%

    No Known Activations