© 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. 12-RES-JB
    11. 3936
    Prev
    Next
    INDEX
    Explanations

    words related to legal organizations or political entities, especially those associated with Christian conservatism

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    the abbreviation "AD" likely related to Alzheimer's disease or Alzheimer's-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     fortunate
    -0.66
    ariat
    -0.63
    otine
    -0.63
    atically
    -0.61
    atis
    -0.61
    iday
    -0.59
     classified
    -0.59
     Fey
    -0.59
    unda
    -0.59
     benef
    -0.58
    POSITIVE LOGITS
    VERTIS
    1.42
    VERTISEMENT
    1.32
    ULTS
    1.24
    MIN
    1.21
    AMS
    1.13
    JUST
    1.10
    VICE
    1.09
    DIS
    1.05
    VIS
    1.03
    ULT
    1.02
    Activations Density 0.025%

    No Known Activations