© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 6704
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Score"

    oai_token-act-pair · gpt-3.5-turbo

    the term "score" and its variations as they relate to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heit
    -0.74
     prevail
    -0.73
     dare
    -0.73
    éĹĺ
    -0.70
     disarm
    -0.69
     restraint
    -0.69
     loose
    -0.65
     Archdemon
    -0.64
     falsehood
    -0.64
    sth
    -0.63
    POSITIVE LOGITS
    apers
    1.12
    urry
    1.11
    opes
    1.10
    ratch
    1.08
    atters
    1.04
    attered
    1.03
    ammers
    1.02
    atter
    1.01
    rupulous
    0.99
    reens
    0.98
    Activations Density 0.003%

    No Known Activations