© 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. 2-RES-JB
    11. 12433
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Henry" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Henry."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.91
    cheon
    -0.80
    unct
    -0.77
    olulu
    -0.76
    ntil
    -0.75
    ãĥ£
    -0.74
    olitan
    -0.74
    ainment
    -0.73
    atively
    -0.73
    awaru
    -0.71
    POSITIVE LOGITS
     Rollins
    1.01
     Kissinger
    0.96
    Henry
    0.95
     Tud
    0.94
     Henry
    0.92
     VIII
    0.91
     Ford
    0.89
     Daniels
    0.81
     Miller
    0.81
     Wad
    0.79
    Activations Density 0.009%

    No Known Activations