© 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. 2-RES-JB
    11. 462
    Prev
    Next
    INDEX
    Explanations

    the word "Show" when it is used as a command or request

    oai_token-act-pair · gpt-4-turbo

    mentions of a specific TV or radio show

    oai_token-act-pair · gpt-3.5-turbo

    references to television shows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -1.05
    fortunately
    -0.75
    ignty
    -0.71
    undai
    -0.71
    assing
    -0.71
    perty
    -0.70
     litter
    -0.70
    ategory
    -0.69
     manif
    -0.69
    iotics
    -0.68
    POSITIVE LOGITS
     Tycoon
    1.15
    biz
    1.15
     Show
    1.10
    runners
    1.02
    Hide
    0.96
    hide
    0.95
    case
    0.94
    Show
    0.93
    grounds
    0.92
    show
    0.92
    Activations Density 0.015%

    No Known Activations