© 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. 7-RES-JB
    11. 9964
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person's name - possibly related to news, legal matters, or events involving this person

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals and their actions or roles within a narrative

    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
    âĸ¬
    -0.74
    bleacher
    -0.70
    endra
    -0.68
    iour
    -0.66
    bread
    -0.65
    kered
    -0.64
     Pebble
    -0.63
    izations
    -0.63
     Chak
    -0.62
    lined
    -0.61
    POSITIVE LOGITS
    ertodd
    1.02
    ERSON
    0.99
    ersen
    0.80
    asus
    0.78
     Peterson
    0.76
    nown
    0.76
    erson
    0.75
    hammad
    0.74
    roleum
    0.74
    olicy
    0.73
    Activations Density 0.033%

    No Known Activations