© 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. 10-RES-JB
    11. 8448
    Prev
    Next
    INDEX
    Explanations

    terms related to dependence or dependency

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥīãĥ©
    -0.68
    vision
    -0.67
     rushes
    -0.64
    AH
    -0.63
    gage
    -0.62
    enium
    -0.60
    sale
    -0.59
    company
    -0.58
    gart
    -0.57
    unic
    -0.57
    POSITIVE LOGITS
     greatly
    1.27
     heavily
    1.23
     enormously
    1.20
     markedly
    1.13
     sharply
    1.13
     tremendously
    1.11
     hugely
    1.11
     prominently
    1.06
     considerably
    1.06
     substantially
    1.05
    Activations Density 0.083%

    No Known Activations