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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 24189
    Prev
    Next
    INDEX
    Explanations

    names specifically ending in "zan"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals with the surname "Zan" or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Limits
    -0.73
     confir
    -0.70
     thous
    -0.68
     follower
    -0.64
    growth
    -0.61
     hemor
    -0.60
     peripher
    -0.60
     includ
    -0.60
     heartbeat
    -0.60
     happ
    -0.59
    POSITIVE LOGITS
    zan
    1.22
    omon
    1.00
    owski
    0.95
    ita
    0.93
    thal
    0.92
    ning
    0.92
    atown
    0.90
    ormal
    0.89
    sey
    0.89
    nikov
    0.88
    Activations Density 0.007%

    No Known Activations