© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 8956
    Prev
    Next
    INDEX
    Explanations

    words related to the term "perm"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "permafrost."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GER
    -0.71
    lycer
    -0.70
    yer
    -0.68
    worthy
    -0.66
     Knights
    -0.65
    llo
    -0.64
     GI
    -0.64
    glers
    -0.64
    raq
    -0.64
    tone
    -0.63
    POSITIVE LOGITS
    utations
    1.16
    ittee
    1.09
     perm
    1.06
    perm
    1.06
    utation
    0.99
    isphere
    0.94
    iton
    0.92
    itic
    0.91
    ittees
    0.91
    itent
    0.89
    Activations Density 0.005%

    No Known Activations