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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 1983
    Prev
    Next
    INDEX
    Explanations

    words related to fax communication

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fax" in various contexts

    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
     immigrants
    -0.70
     heap
    -0.68
     Cand
    -0.67
     Native
    -0.64
     predomin
    -0.62
     ent
    -0.62
     core
    -0.62
    ICAN
    -0.61
     stagnant
    -0.61
     lazy
    -0.61
    POSITIVE LOGITS
    fax
    5.11
    Fax
    2.01
     fax
    1.37
    yip
    1.02
    ibaba
    0.98
    fman
    0.97
     Fairfax
    0.94
    DragonMagazine
    0.93
    plom
    0.90
    mail
    0.87
    Activations Density 0.021%

    No Known Activations