© 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. 10-RES-JB
    11. 5936
    Prev
    Next
    INDEX
    Explanations

    locations or military bases with the word "Fort" in their names

    oai_token-act-pair · gpt-3.5-turbo

    references to different military forts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.61
    henko
    -0.61
    Companies
    -0.60
    senal
    -0.60
    gger
    -0.60
    pert
    -0.58
    Accessory
    -0.57
     polarized
    -0.56
     Primordial
    -0.55
     chromosomes
    -0.55
    POSITIVE LOGITS
     Lauderdale
    1.27
    uitous
    1.27
    itude
    1.22
    ieth
    1.15
    resses
    1.00
     Worth
    1.00
    dinand
    0.97
    itud
    0.96
    itudes
    0.90
    anamo
    0.88
    Activations Density 0.024%

    No Known Activations