© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 21567
    Prev
    Next
    INDEX
    Explanations

    numbers or numerical values indicating achievement or performance levels

    oai_token-act-pair · gpt-3.5-turbo

    mentions of sports championships and titles won

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >[
    -0.80
    ffer
    -0.71
    ngth
    -0.68
    anwhile
    -0.68
    illation
    -0.67
     arrival
    -0.66
    fff
    -0.64
     Presence
    -0.64
    response
    -0.63
     backdrop
    -0.63
    POSITIVE LOGITS
     championships
    1.17
     trophies
    1.16
     prizes
    1.09
     medals
    1.07
     titles
    1.05
     awards
    1.04
     contests
    0.97
     Cups
    0.97
     competitions
    0.92
     tournaments
    0.90
    Activations Density 0.114%

    No Known Activations