© 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 EvalsExportsAPI 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. 13828
    Prev
    Next
    INDEX
    Explanations

    mentions of the concept of creationism

    oai_token-act-pair · gpt-3.5-turbo

    terms related to creationism and its educational implications

    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
     nails
    -0.69
    hester
    -0.64
     brakes
    -0.61
     bribes
    -0.58
    ÅĤ
    -0.58
     teasp
    -0.58
    restling
    -0.58
     CTR
    -0.57
    âĸĵ
    -0.56
    ipeg
    -0.56
    POSITIVE LOGITS
    vez
    0.60
     Oo
    0.58
     coli
    0.56
     Thumbnails
    0.55
     guiActiveUnfocused
    0.54
    esm
    0.54
     populate
    0.53
    ensis
    0.53
    ãĤ¨ãĥ«
    0.53
    alian
    0.51
    Activations Density 1.334%

    No Known Activations