© 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. 6-RES-JB
    11. 9921
    Prev
    Next
    INDEX
    Explanations

    the specific word "irt" with varying degrees of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "virtue" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ILCS
    -0.68
     reckoning
    -0.67
    interrupted
    -0.67
    ŃĶ
    -0.62
    cffffcc
    -0.62
    ¬¼
    -0.62
    ULT
    -0.61
    ©¶æ
    -0.59
    sych
    -0.59
    living
    -0.59
    POSITIVE LOGITS
    ually
    0.96
    entials
    0.96
    alia
    0.90
    ilde
    0.89
    inyl
    0.86
    ables
    0.82
    ieth
    0.82
    ullah
    0.80
    igue
    0.79
    ilda
    0.78
    Activations Density 0.025%

    No Known Activations