© 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 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. 10-RES-JB
    11. 4920
    Prev
    Next
    INDEX
    Explanations

    words related to a specific TV channel or network

    oai_token-act-pair · gpt-3.5-turbo

    references to the Syfy television network or its programming

    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
    wagen
    -0.69
    ORED
    -0.66
    IFIED
    -0.64
     captcha
    -0.63
     compliment
    -0.60
     approving
    -0.60
     admission
    -0.59
     Hots
    -0.58
     unemployment
    -0.58
    orage
    -0.57
    POSITIVE LOGITS
    lves
    1.42
    philis
    1.36
    bil
    1.35
    nerg
    1.32
    ringe
    1.31
    nergy
    1.30
    mbol
    1.28
    mp
    1.14
    ntax
    1.13
    rup
    1.12
    Activations Density 0.024%

    No Known Activations