© 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. 10-RES-JB
    11. 6248
    Prev
    Next
    INDEX
    Explanations

    verbs related to research or investigation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to research and investigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    anya
    -0.77
    Lago
    -0.74
    Evil
    -0.72
    Hon
    -0.71
    à¥
    -0.69
    END
    -0.69
    corn
    -0.69
    æł
    -0.67
    ief
    -0.67
    borgh
    -0.67
    POSITIVE LOGITS
     whether
    1.54
     how
    1.46
     why
    1.24
     correlations
    1.17
    whether
    1.14
     ways
    1.13
     factors
    1.10
     mechanisms
    1.10
     trends
    1.06
     WHY
    1.05
    Activations Density 0.165%

    No Known Activations