© 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. 7-RES-JB
    11. 20646
    Prev
    Next
    INDEX
    Explanations

    mentions of the pharmaceutical company "Merck"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific pharmaceutical company

    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
    »Ĵ
    -0.72
     IMAGES
    -0.70
    ¬¼
    -0.67
    YE
    -0.65
     Âł Âł Âł Âł Âł Âł Âł Âł
    -0.63
    IGHTS
    -0.62
     Eliot
    -0.61
     Siege
    -0.61
     Fathers
    -0.60
     matter
    -0.59
    POSITIVE LOGITS
    cedes
    1.15
    seys
    1.03
    maid
    1.03
    lins
    1.02
    chant
    1.02
    gers
    1.02
    ril
    0.99
    itism
    0.98
    ged
    0.97
    rill
    0.95
    Activations Density 0.025%

    No Known Activations