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. 8539
    Prev
    Next
    INDEX
    Explanations

    terms related to a group of people working together

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a group of individuals working together, specifically a crew

    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
    mobi
    -0.77
     Fem
    -0.67
     ISI
    -0.66
    ãĥ¤
    -0.66
     Tend
    -0.66
    akeru
    -0.66
    ibaba
    -0.64
     arous
    -0.64
     Kush
    -0.64
    pire
    -0.63
    POSITIVE LOGITS
    members
    1.33
    member
    1.10
    mates
    1.05
    wreck
    0.94
     crew
    0.94
     crews
    0.85
     mates
    0.84
     chiefs
    0.81
     cabin
    0.80
    smanship
    0.79
    Activations Density 0.009%

    No Known Activations