© 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. 2-RES-JB
    11. 16109
    Prev
    Next
    INDEX
    Explanations

    the name "Zeger" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ze"

    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
     behavi
    -0.79
    ials
    -0.70
     à¨
    -0.70
     ancest
    -0.68
    ancial
    -0.66
    Interstitial
    -0.66
    paced
    -0.65
     SERV
    -0.64
    yards
    -0.64
     conduc
    -0.63
    POSITIVE LOGITS
    lda
    1.27
    ppelin
    1.17
    ze
    1.02
    ppe
    0.98
    zinski
    0.93
    ÅĤ
    0.93
    enza
    0.91
    zza
    0.91
    ppo
    0.89
    eker
    0.87
    Activations Density 0.009%

    No Known Activations