© 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. 9586
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names with the prefix "per"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "per" in various contexts

    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
     Carbuncle
    -0.71
     Roche
    -0.64
    ADRA
    -0.62
    ä¸ī
    -0.62
    MpServer
    -0.62
     pneum
    -0.61
    å¸
    -0.60
     Alm
    -0.60
     Aval
    -0.60
    ilda
    -0.59
    POSITIVE LOGITS
    due
    1.02
    manent
    0.97
    cussion
    0.96
    jury
    0.95
    secution
    0.93
    taining
    0.93
    ipher
    0.91
    mission
    0.91
    uvian
    0.91
    missible
    0.90
    Activations Density 0.007%

    No Known Activations