© 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. 10-RES-JB
    6. 20614
    Prev
    Next
    INDEX
    Explanations

    the word "tent" at varying levels of strength

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "tent."

    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
    course
    -0.65
    ÃĽ
    -0.64
    Course
    -0.63
     Emin
    -0.63
     beet
    -0.62
     Uz
    -0.60
     caut
    -0.60
     symmetry
    -0.60
     Cuomo
    -0.59
     fats
    -0.59
    POSITIVE LOGITS
    acle
    1.49
    atively
    1.41
    pole
    1.34
    acles
    1.16
    acular
    1.14
     encamp
    0.97
    acly
    0.96
     poles
    0.94
    pipe
    0.89
     pole
    0.87
    Activations Density 0.047%

    No Known Activations