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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4410
    Prev
    Next
    INDEX
    Explanations

    terms related to saccharomyces, specifically focusing on activities like fermentation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to different fields of study or sciences, particularly those involving 'omy' suffixes

    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
    ividual
    -0.77
    leased
    -0.71
    posted
    -0.70
     Leilan
    -0.68
    eded
    -0.66
    inyl
    -0.66
    added
    -0.63
    aneously
    -0.63
    ript
    -0.62
    ãģį
    -0.62
    POSITIVE LOGITS
    omy
    1.35
    gdala
    1.03
    ogy
    0.93
    algia
    0.87
    elia
    0.83
    cular
    0.76
    opathy
    0.76
    olit
    0.73
    opy
    0.72
    ophobia
    0.71
    Activations Density 0.008%

    No Known Activations