© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3401
    Prev
    Next
    INDEX
    Explanations

    terms related to proposed changes or reforms

    oai_token-act-pair · gpt-3.5-turbo

    references to proposed changes or amendments in laws and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irection
    -0.69
    andestine
    -0.64
    rum
    -0.63
    going
    -0.63
    croft
    -0.62
    pires
    -0.61
    sky
    -0.60
    nder
    -0.60
    pection
    -0.60
     &
    -0.57
    POSITIVE LOGITS
     ensure
    1.51
     accommodate
    1.47
     counteract
    1.46
     compensate
    1.43
     appease
    1.43
     mitigate
    1.42
     enhance
    1.40
     facilitate
    1.40
     improve
    1.40
     achieve
    1.39
    Activations Density 0.356%

    No Known Activations