© 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. 8-RES-JB
    11. 14919
    Prev
    Next
    INDEX
    Explanations

    famous people's names ending with 'ha'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of "ha" which likely indicate laughter or amusement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atories
    -0.80
    night
    -0.67
    rations
    -0.67
     outgoing
    -0.65
    inarily
    -0.64
    é»Ĵ
    -0.63
    bats
    -0.63
    lio
    -0.61
     Collider
    -0.60
    rats
    -0.60
    POSITIVE LOGITS
    wn
    1.23
    user
    1.15
    illard
    1.00
    emi
    0.98
    pless
    0.94
    irst
    0.91
    azard
    0.90
    ild
    0.89
    arma
    0.88
    ifa
    0.88
    Activations Density 0.034%

    No Known Activations