© 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. 9-RES-JB
    11. 7320
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically related to a security agency called "Shin Bet."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Shin," specifically in the context of "Shin Bet" and related subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aneers
    -0.80
    theless
    -0.77
    anwhile
    -0.76
    enance
    -0.76
    ieu
    -0.70
    nesday
    -0.68
    ENCE
    -0.68
    iments
    -0.67
    estial
    -0.66
    dit
    -0.65
    POSITIVE LOGITS
    obi
    0.91
    ogi
    0.88
    pei
    0.84
    roud
    0.80
     Tsu
    0.76
    ikh
    0.76
    pload
    0.76
    hei
    0.75
    IELD
    0.74
    ichi
    0.74
    Activations Density 0.066%

    No Known Activations