© 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. 7-RES-JB
    11. 23562
    Prev
    Next
    INDEX
    Explanations

    phrases related to proper nouns, particularly those related to political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "cond" and its variations in different contexts

    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
    chy
    -0.70
    kaya
    -0.69
    ngth
    -0.68
    ment
    -0.64
    ku
    -0.63
    manship
    -0.63
    DW
    -0.63
    Sham
    -0.62
    DIR
    -0.60
     bul
    -0.60
    POSITIVE LOGITS
    ominium
    1.20
    enser
    1.19
    ensation
    1.13
    ensed
    1.12
    ensing
    1.04
    uctor
    1.00
    itions
    0.99
    itional
    0.97
    uits
    0.93
    secut
    0.86
    Activations Density 0.028%

    No Known Activations