© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 603
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "snark" or similar variants

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sn" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.92
     Berman
    -0.81
     Alma
    -0.79
     Indra
    -0.71
    rika
    -0.70
    ciples
    -0.69
    imar
    -0.68
     Conver
    -0.68
    ür
    -0.68
     Hath
    -0.67
    POSITIVE LOGITS
     sn
    3.38
    sn
    2.09
    Sn
    2.08
     Sn
    2.07
     sniff
    1.75
     sne
    1.69
     snail
    1.69
     scoop
    1.29
     sque
    1.28
     snatch
    1.27
    Activations Density 0.015%

    No Known Activations