© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-JB
    11. 10504
    Prev
    Next
    INDEX
    Explanations

    words related to an electronic device or brand named "Mic."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Mic", which may refer to a microphone or specific product name

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

    No Comments

    Negative Logits
    ACTED
    -0.84
    ãĤĤ
    -0.74
    DragonMagazine
    -0.73
    20439
    -0.72
    é»Ĵ
    -0.71
    BuyableInstoreAndOnline
    -0.71
    ãģ®éŃĶ
    -0.70
    ãģĮ
    -0.69
    ĪĴ
    -0.69
    tenance
    -0.68
    POSITIVE LOGITS
    onductor
    1.05
    rones
    1.01
    ron
    0.94
    olon
    0.94
    ropolitan
    0.93
    roman
    0.93
    HAEL
    0.92
    onduct
    0.91
    rodu
    0.90
    nic
    0.89
    Activations Density 0.007%

    No Known Activations