© 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. 7-RES-JB
    11. 1509
    Prev
    Next
    INDEX
    Explanations

    technical terms and keywords related to software development and standards

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications and standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Osiris
    -0.80
    yss
    -0.72
     healer
    -0.71
     Ukrain
    -0.71
    resp
    -0.71
    pring
    -0.70
     Kinnikuman
    -0.69
     worsh
    -0.69
    ilon
    -0.69
     psychic
    -0.68
    POSITIVE LOGITS
     regulations
    1.11
     Regulations
    1.09
     amendments
    1.08
     Amendments
    1.07
     legislation
    1.06
     amend
    1.05
     mandates
    1.03
    Draft
    1.02
     provisions
    1.02
     guidelines
    1.01
    Activations Density 0.514%

    No Known Activations