© 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. 2-RES-JB
    11. 8918
    Prev
    Next
    INDEX
    Explanations

    proper names, with a specific emphasis on the name "Helen"

    oai_token-act-pair · gpt-3.5-turbo

    names of notable individuals and organizations, particularly "Helen" and "JPMorgan."

    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
     Rebels
    -0.79
    arro
    -0.76
    arthed
    -0.75
    asted
    -0.75
    nir
    -0.74
    igators
    -0.74
    andi
    -0.74
    agen
    -0.73
    aid
    -0.73
    Rated
    -0.72
    POSITIVE LOGITS
     serotonin
    0.81
    teness
    0.78
    cephal
    0.76
     wrench
    0.74
     crate
    0.72
     dam
    0.70
     mosqu
    0.70
     coffin
    0.69
     Helen
    0.69
    ï¸
    0.69
    Activations Density 0.020%

    No Known Activations