© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 2981
    Prev
    Next
    INDEX
    Explanations

    phrases related to tuning or tuning in

    oai_token-act-pair · gpt-3.5-turbo

    references to tuning or adjusting something, especially in a media context

    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
    lain
    -0.74
    inals
    -0.71
    perse
    -0.69
    TPPStreamerBot
    -0.68
    quez
    -0.67
    ãĤ¨ãĥ«
    -0.67
    anmar
    -0.67
    soever
    -0.66
     miscar
    -0.64
    pha
    -0.62
    POSITIVE LOGITS
     tune
    1.08
     tuned
    1.02
     tunes
    0.97
     Tune
    0.92
     tuning
    0.91
     tun
    0.84
    tun
    0.82
     horns
    0.81
    eness
    0.78
    edo
    0.74
    Activations Density 0.035%

    No Known Activations