© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 2240
    Prev
    Next
    INDEX
    Explanations

    numeric references to years or dates

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years and seasons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Skinner
    -0.72
    acci
    -0.72
     bip
    -0.64
     fret
    -0.61
     brut
    -0.58
     monop
    -0.57
     crate
    -0.57
    obbies
    -0.56
    vertisement
    -0.56
     cumbers
    -0.55
    POSITIVE LOGITS
    GV
    0.82
    âĢ¢âĢ¢
    0.80
    é¾į
    0.74
     edition
    0.71
    igation
    0.69
    å¹
    0.69
     editions
    0.67
    yond
    0.65
    GAN
    0.64
     Nicol
    0.63
    Activations Density 0.197%

    No Known Activations