© 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. 3-RES-JB
    11. 12213
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to setting records or breaking records

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to record-breaking events or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulp
    -0.82
    ogical
    -0.74
     Mandal
    -0.68
    erva
    -0.67
    egal
    -0.66
    udo
    -0.66
    atively
    -0.64
    ULE
    -0.64
    alez
    -0.64
    ORTS
    -0.63
    POSITIVE LOGITS
    fast
    1.17
    breaking
    1.11
    breakers
    0.99
    break
    0.95
    down
    0.87
    beat
    0.85
    downs
    0.82
    breaks
    0.80
    through
    0.80
    Berry
    0.79
    Activations Density 0.010%

    No Known Activations