© 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. 4-RES-JB
    11. 1247
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "permutation"

    oai_token-act-pair · gpt-3.5-turbo

    references to 'permafrost' and related concepts

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

    No Comments

    Negative Logits
    yer
    -0.71
    worthy
    -0.68
     Gorge
    -0.67
    VERTIS
    -0.65
    roads
    -0.65
     Wiley
    -0.64
     GI
    -0.64
    yahoo
    -0.63
    rider
    -0.62
    osterone
    -0.62
    POSITIVE LOGITS
    utations
    1.20
    ittee
    1.08
    utation
    1.02
    isphere
    1.01
    essage
    1.00
    iton
    0.97
    perm
    0.97
     perm
    0.95
    itent
    0.95
    ittees
    0.93
    Activations Density 0.007%

    No Known Activations