© 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. 0-RES-JB
    11. 8229
    Prev
    Next
    INDEX
    Explanations

    words related to names and titles with a focus on the suffix "am" or similar patterns

    oai_token-act-pair · gpt-3.5-turbo

    the word "am" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ISI
    -0.68
     rall
    -0.67
    æł
    -0.63
     Skydragon
    -0.61
     transitions
    -0.61
     frontline
    -0.60
     phyl
    -0.60
     Brow
    -0.58
    ãģ®éŃĶ
    -0.58
     line
    -0.58
    POSITIVE LOGITS
    am
    3.97
    AM
    2.28
    ams
    2.15
    amic
    2.00
    amia
    1.97
    ammy
    1.94
    amar
    1.84
    amin
    1.82
    amation
    1.79
    amate
    1.66
    Activations Density 0.023%

    No Known Activations