© 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. 2245
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences beginning with "An" followed by a proper noun

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "An."

    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
    heimer
    -0.65
    seys
    -0.64
    ITNESS
    -0.64
     tack
    -0.60
    ows
    -0.59
     loser
    -0.59
    rue
    -0.58
    VILLE
    -0.58
    croft
    -0.58
    ãģ®éŃĶ
    -0.58
    POSITIVE LOGITS
     An
    2.98
    An
    1.92
     AN
    1.61
     A
    1.50
     Ank
    1.20
     As
    1.18
     Ana
    1.18
     At
    1.05
     Amid
    1.05
     Anat
    1.03
    Activations Density 0.014%

    No Known Activations