© 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. 15098
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical conditions and treatments

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to biology and cellular structures

    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
     reluct
    -0.66
    ¥
    -0.65
     volunte
    -0.64
     elig
    -0.63
     disadvant
    -0.63
     adolescent
    -0.62
     newsp
    -0.62
    dL
    -0.61
     unden
    -0.60
    oulos
    -0.59
    POSITIVE LOGITS
    worm
    1.14
    fish
    1.06
    worms
    1.04
    cloth
    1.03
    less
    0.98
    tailed
    0.91
    weed
    0.91
    bean
    0.90
    tail
    0.90
    pipe
    0.89
    Activations Density 0.384%

    No Known Activations