© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 15102
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the word "Park"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific park or location

    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
     dilig
    -0.70
    nces
    -0.68
    minded
    -0.64
    omething
    -0.64
    apter
    -0.63
    nant
    -0.63
     Cald
    -0.60
    interstitial
    -0.57
    xit
    -0.57
    ilian
    -0.56
    POSITIVE LOGITS
    conservancy
    0.93
    hurst
    0.93
    our
    0.92
    lands
    0.89
    itect
    0.88
    park
    0.88
    walk
    0.87
    walking
    0.84
    walker
    0.84
    lease
    0.84
    Activations Density 0.050%

    No Known Activations