© 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. 10-RES-JB
    11. 18964
    Prev
    Next
    INDEX
    Explanations

    phrases related to television shows

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific TV show

    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
     solitary
    -0.75
    illard
    -0.68
    illet
    -0.65
     annexed
    -0.65
     saline
    -0.63
     Lucia
    -0.62
     steel
    -0.61
     reef
    -0.61
     STATES
    -0.60
     Aval
    -0.60
    POSITIVE LOGITS
    runners
    1.68
    biz
    1.62
    runner
    1.56
    manship
    1.36
    downs
    1.25
    room
    1.13
    case
    1.12
    mable
    1.12
    rooms
    1.06
    cases
    1.05
    Activations Density 0.045%

    No Known Activations