© 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. 7-RES-JB
    11. 23934
    Prev
    Next
    INDEX
    Explanations

    references to individuals or things being idolized or celebrated

    oai_token-act-pair · gpt-3.5-turbo

    references to idols and celebrity culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hire
    -0.95
    es
    -0.84
    hid
    -0.79
    hou
    -0.75
    rooms
    -0.74
    yards
    -0.74
    berra
    -0.71
    oning
    -0.70
    cale
    -0.70
    externalActionCode
    -0.69
    POSITIVE LOGITS
    inating
    0.86
    otive
    0.84
    ãĤ§
    0.83
    izable
    0.81
    inated
    0.80
    BALL
    0.78
    ãĥ¤
    0.76
    9999
    0.76
    yrinth
    0.74
    inatory
    0.74
    Activations Density 0.073%

    No Known Activations