© 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. 9-RES-JB
    11. 15982
    Prev
    Next
    INDEX
    Explanations

    responses to requests for comments or information

    oai_token-act-pair · gpt-3.5-turbo

    instances of individuals or entities not responding to requests for comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĪ¦
    -0.67
    士
    -0.64
    èĢħ
    -0.64
     harness
    -0.60
    iatric
    -0.60
    Exper
    -0.59
    ardless
    -0.57
    èĢ
    -0.57
    usterity
    -0.56
    unning
    -0.56
    POSITIVE LOGITS
     requests
    1.07
     inquiries
    0.96
     request
    0.92
     repeated
    0.88
     queries
    0.88
     emailed
    0.85
     telephone
    0.79
     phone
    0.79
     HuffPost
    0.78
     newsp
    0.77
    Activations Density 0.080%

    No Known Activations