© 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. 6-RES-JB
    11. 1542
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Morrison" with a high activation value

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those named Morrison or Newman

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¡
    -0.81
    liest
    -0.80
    rique
    -0.78
    abet
    -0.78
    Ľ
    -0.75
    coon
    -0.75
    rolog
    -0.75
    rik
    -0.75
    pering
    -0.74
    ility
    -0.74
    POSITIVE LOGITS
    ufact
    0.91
     Leilan
    0.79
    idge
    0.77
     AFB
    0.76
    igon
    0.75
    inez
    0.71
     Lennon
    0.71
    istic
    0.70
    isms
    0.70
     Soup
    0.69
    Activations Density 0.060%

    No Known Activations