© 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. 11-RES-JB
    11. 1126
    Prev
    Next
    INDEX
    Explanations

    phrases related to checking for specific items or conditions

    oai_token-act-pair · gpt-3.5-turbo

    instances of verification or inspection processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.90
    haw
    -0.81
    anan
    -0.72
    amera
    -0.72
    arak
    -0.71
    andowski
    -0.70
    minus
    -0.70
    wikipedia
    -0.69
    lvl
    -0.69
     Canaver
    -0.69
    POSITIVE LOGITS
     abnormalities
    1.34
     anomalies
    1.25
     signs
    1.22
     contaminants
    1.20
     defects
    1.18
     deviations
    1.15
     irregularities
    1.14
     clues
    1.13
     weaknesses
    1.12
     tampering
    1.12
    Activations Density 0.206%

    No Known Activations