© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16026
    Prev
    Next
    INDEX
    Explanations

    proper nouns starting with the letter "I"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "Is" in various contexts

    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
    IOR
    -0.73
    theless
    -0.70
     Hots
    -0.63
    ãģĮ
    -0.62
     Lann
    -0.59
     digs
    -0.59
     stakes
    -0.58
    ruciating
    -0.58
     Handler
    -0.58
     IMAGES
    -0.57
    POSITIVE LOGITS
    olation
    1.61
    olated
    1.54
    rael
    1.39
    olate
    1.39
    abella
    1.24
    peria
    1.17
    abel
    1.16
    sei
    1.13
    htar
    1.10
    senal
    1.10
    Activations Density 0.068%

    No Known Activations