© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 11758
    Prev
    Next
    INDEX
    Explanations

    keywords related to the television channel "Syfy."

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "Sy" likely related to a specific brand or program

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unemployment
    -0.62
     captcha
    -0.60
    IFIED
    -0.60
    wagen
    -0.60
    ORED
    -0.59
     supreme
    -0.57
    ional
    -0.56
     Transgender
    -0.56
    yout
    -0.56
    inarily
    -0.56
    POSITIVE LOGITS
    lves
    1.55
    philis
    1.42
    bil
    1.38
    nergy
    1.35
    ringe
    1.32
    kes
    1.28
    nerg
    1.27
    mbol
    1.25
    rup
    1.19
    ntax
    1.18
    Activations Density 0.033%

    No Known Activations