© 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
    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. 6032
    Prev
    Next
    INDEX
    Explanations

    phrases with apostrophes and contractions

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol

    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
     Skydragon
    -0.60
     mathemat
    -0.58
     Gaul
    -0.57
     fortun
    -0.56
     Mobil
    -0.55
     Samar
    -0.54
     Mirage
    -0.54
     Gmail
    -0.52
     Palestin
    -0.52
     Papua
    -0.52
    POSITIVE LOGITS
    s
    0.86
    sure
    0.85
    ï¸ı
    0.83
    t
    0.78
    ear
    0.76
    ski
    0.76
    tis
    0.74
    mad
    0.74
    else
    0.74
    ved
    0.74
    Activations Density 0.383%

    No Known Activations