© 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. 8333
    Prev
    Next
    INDEX
    Explanations

    mentions of specific numbers and statistics

    oai_token-act-pair · gpt-3.5-turbo

    references to specific ages or generations

    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
     welfare
    -0.75
    Merit
    -0.68
     disadvant
    -0.67
     mosqu
    -0.67
    etooth
    -0.67
     vocational
    -0.65
    ¬¼
    -0.65
    à¦
    -0.64
    ulic
    -0.63
     administr
    -0.62
    POSITIVE LOGITS
     sequels
    1.07
     Whedon
    1.06
    episode
    1.01
     Kubrick
    1.01
     cinematic
    0.99
    Marvel
    0.98
     spoilers
    0.98
     Spielberg
    0.98
    canon
    0.96
     soundtrack
    0.96
    Activations Density 1.537%

    No Known Activations