© 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. 2-RES-JB
    11. 13621
    Prev
    Next
    INDEX
    Explanations

    the name "Moll" followed by various words or suffixes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Kollock" and its variations

    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
    £ı
    -0.72
    ¥µ
    -0.67
     Flavoring
    -0.66
    QUIRE
    -0.65
    âĸ¬âĸ¬
    -0.64
     magnification
    -0.63
    POR
    -0.63
    ©¶æ
    -0.63
    âĸ¬
    -0.62
    cipled
    -0.62
    POSITIVE LOGITS
    ipop
    1.41
    inson
    1.11
    ieu
    0.99
    oll
    0.92
    ogue
    0.92
    enstein
    0.92
    oyd
    0.90
    ogy
    0.89
    ega
    0.89
    iard
    0.89
    Activations Density 0.009%

    No Known Activations