© 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. 8-RES-JB
    11. 7825
    Prev
    Next
    INDEX
    Explanations

    the name "Sar" followed by a variety of different suffixes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Sar" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flourish
    -0.70
     Lovecraft
    -0.69
    YC
    -0.68
     curfew
    -0.67
    éĹĺ
    -0.65
    STER
    -0.64
     burgeoning
    -0.60
     Dangerous
    -0.60
    ELS
    -0.58
    iculty
    -0.58
    POSITIVE LOGITS
    kees
    1.33
    wark
    1.12
    andon
    1.09
    vey
    1.00
    ban
    0.98
    vati
    0.98
    vation
    0.97
    abeth
    0.96
    ona
    0.95
    uba
    0.94
    Activations Density 0.034%

    No Known Activations