© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 395
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "geeks" or related variations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of 'geeks'

    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
    PLA
    -0.77
     corrid
    -0.73
    Ec
    -0.72
    ãģĤ
    -0.66
    mine
    -0.64
     bilateral
    -0.64
     corridors
    -0.63
     sheets
    -0.60
    less
    -0.60
     relations
    -0.59
    POSITIVE LOGITS
    haw
    1.12
    paces
    1.08
    kies
    1.07
    poons
    1.03
    uggest
    1.00
    eeks
    0.99
    chool
    0.99
    cale
    0.98
    hots
    0.97
    ilver
    0.97
    Activations Density 0.039%

    No Known Activations