© 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. 11-RES-JB
    11. 20415
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Fred" at a strong activation level

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Fred."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Depth
    -0.64
     action
    -0.62
     indoors
    -0.60
     tone
    -0.60
    BOOK
    -0.59
     SOC
    -0.59
     secretary
    -0.59
    utes
    -0.59
     chemistry
    -0.58
    pell
    -0.58
    POSITIVE LOGITS
    erick
    1.39
    rik
    1.35
    riks
    1.33
    rick
    1.32
    ricks
    1.29
    ric
    1.18
    die
    1.12
    rique
    1.06
    rica
    1.04
    dy
    1.02
    Activations Density 0.034%

    No Known Activations