© 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. 7-RES-JB
    11. 12705
    Prev
    Next
    INDEX
    Explanations

    mentions of notable individuals, particularly those with a strong association with the name "Albert", like "Albert Einstein"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Albert," particularly associated with notable figures such as Albert Einstein

    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
    BOOK
    -0.86
    ãĥ¯
    -0.81
    ned
    -0.78
    osuke
    -0.78
    ning
    -0.74
    pter
    -0.72
    efully
    -0.71
    ners
    -0.69
    mble
    -0.68
    ettlement
    -0.68
    POSITIVE LOGITS
     Einstein
    1.18
     Pu
    0.81
     Calder
    0.76
     Schwe
    0.75
    inas
    0.75
    onso
    0.73
    inates
    0.72
    rand
    0.72
     Hammond
    0.72
    anus
    0.69
    Activations Density 0.022%

    No Known Activations