© 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. 4-RES-JB
    11. 22314
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Mollie" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "oll."

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

    No Comments

    Negative Logits
    PDATE
    -0.73
     Flavoring
    -0.72
    ©¶æ
    -0.68
     exha
    -0.66
    ãĥ£
    -0.66
    £ı
    -0.66
     quo
    -0.65
    rament
    -0.65
    rano
    -0.64
    âĸ¬
    -0.64
    POSITIVE LOGITS
    ipop
    1.33
    inson
    0.93
    iard
    0.93
    oning
    0.92
    sburgh
    0.92
    ieu
    0.91
    ocks
    0.88
    enstein
    0.88
    ocations
    0.86
    ega
    0.85
    Activations Density 0.009%

    No Known Activations