© 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. 1-RES-JB
    11. 1333
    Prev
    Next
    INDEX
    Explanations

    words related to credibility and invisibility

    oai_token-act-pair · gpt-3.5-turbo

    variations of the concept of "ability" or "capability."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.81
    battle
    -0.72
    ighth
    -0.68
    alogue
    -0.67
    ACH
    -0.65
    ãģį
    -0.65
    birth
    -0.63
    attacks
    -0.62
    Franc
    -0.62
    ghazi
    -0.61
    POSITIVE LOGITS
    ibility
    1.63
    ibilities
    1.25
    ibly
    1.09
    xtap
    0.92
    ible
    0.89
    IBLE
    0.88
    osate
    0.85
    ibles
    0.83
    ibl
    0.81
    ulnerability
    0.77
    Activations Density 0.018%

    No Known Activations