© 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. 23806
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals and entities

    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
    anooga
    -0.70
    ertain
    -0.68
     Corpus
    -0.67
    gom
    -0.65
    asia
    -0.61
    orporated
    -0.61
    ovies
    -0.60
    ":[
    -0.60
    terson
    -0.60
     Lima
    -0.60
    POSITIVE LOGITS
    senal
    1.46
    cliffe
    0.88
    uling
    0.81
    haps
    0.80
    fect
    0.78
    ansom
    0.77
    ascal
    0.76
    kj
    0.73
    interstitial
    0.73
    utherford
    0.71
    Activations Density 0.175%

    No Known Activations