© 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 EvalsExportsinterp-engineNEWAPI 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. 7-RES-JB
    11. 14549
    Prev
    Next
    INDEX
    Explanations

    locations or proper nouns containing the letters "ina"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ina" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ²¾
    -0.81
    yright
    -0.80
    matically
    -0.78
    acular
    -0.77
    geoning
    -0.72
    ansas
    -0.72
    NING
    -0.71
    VERTISEMENT
    -0.71
    sterdam
    -0.70
    irlf
    -0.70
    POSITIVE LOGITS
    fter
    1.00
    cious
    0.95
    BILITY
    0.93
     Fey
    0.90
     Rica
    0.86
    ppa
    0.84
    udi
    0.83
     Fas
    0.81
    ux
    0.79
    eus
    0.79
    Activations Density 0.046%

    No Known Activations