© 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. 3491
    Prev
    Next
    INDEX
    Explanations

    phrases related to making claims or asserting ownership

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to claims or assertions made by individuals or groups

    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
    omb
    -0.60
    vous
    -0.60
    Newsletter
    -0.59
    pol
    -0.59
    sterdam
    -0.58
    ordon
    -0.58
    patch
    -0.57
    ilings
    -0.57
    onen
    -0.56
    urations
    -0.56
    POSITIVE LOGITS
     responsibility
    1.13
     innocence
    1.09
     ownership
    0.96
     allegiance
    0.95
     ignorance
    0.94
     credit
    0.92
     respons
    0.87
     superiority
    0.84
     victory
    0.83
    independence
    0.83
    Activations Density 0.075%

    No Known Activations