© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7951
    Prev
    Next
    INDEX
    Explanations

    proper names 'Henry' preceded by a number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences 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 @ 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
    ntil
    -0.96
    ramid
    -0.95
    awaru
    -0.94
    cheon
    -0.85
    */(
    -0.84
    ãĤ±
    -0.82
    ãĥ£
    -0.82
    umbai
    -0.81
    cedented
    -0.80
    atively
    -0.79
    POSITIVE LOGITS
     Kissinger
    1.05
     Rollins
    1.04
     Tud
    1.03
     VIII
    0.99
     Ford
    0.92
     Wad
    0.86
     Miller
    0.85
     Hath
    0.83
    ford
    0.81
    shire
    0.79
    Activations Density 0.024%

    No Known Activations