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. 3-RES-JB
    6. 787
    Prev
    Next
    INDEX
    Explanations

    mentions of a group of vehicles or ships

    oai_token-act-pair · gpt-3.5-turbo

    mentions of fleets and related logistics

    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
    Crime
    -0.74
    pheus
    -0.71
    Downloadha
    -0.70
     Extrem
    -0.69
     Hussein
    -0.68
    ividual
    -0.67
    lihood
    -0.67
    argon
    -0.66
    ivas
    -0.66
    mary
    -0.64
    POSITIVE LOGITS
     fleet
    0.89
     fleets
    0.83
     deployments
    0.74
    fleet
    0.73
     squadron
    0.73
     Fleet
    0.72
     mates
    0.72
    Fle
    0.72
    mates
    0.71
    heed
    0.71
    Activations Density 0.014%

    No Known Activations