© 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. 18442
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to specific names, potentially related to locations or people

    oai_token-act-pair · gpt-3.5-turbo

    references to different species of Pokémon

    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
     Subtle
    -0.69
     Satanic
    -0.66
    hower
    -0.62
    chell
    -0.61
     Prohibition
    -0.61
     spirited
    -0.60
     mitigating
    -0.60
     Primal
    -0.59
    ãĥ¼ãĥĨãĤ£
    -0.59
     prohibition
    -0.59
    POSITIVE LOGITS
    ibrarian
    1.35
    ifestyle
    1.31
    yrics
    1.27
    ateral
    1.27
    ighthouse
    1.25
    ayers
    1.25
    arger
    1.24
    aptop
    1.23
    ongevity
    1.22
    ifest
    1.20
    Activations Density 0.032%

    No Known Activations