© 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. 3-RES-JB
    11. 9142
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names, particularly related to "Fletcher" and "Wesley."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    egal
    -0.77
    haps
    -0.74
    DNA
    -0.74
    ossier
    -0.74
    ept
    -0.72
    ocrine
    -0.71
    heimer
    -0.71
    eny
    -0.67
    ibel
    -0.67
    odium
    -0.66
    POSITIVE LOGITS
     Fletcher
    1.17
    letcher
    1.09
    bilt
    0.75
    ttes
    0.75
    reet
    0.72
     Phant
    0.71
    owship
    0.70
    umbai
    0.68
     Torment
    0.66
    ulla
    0.66
    Activations Density 0.011%

    No Known Activations