© 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
    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. 11107
    Prev
    Next
    INDEX
    Explanations

    phrases related to a place or person named "Par" with varying activation strengths

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "Par" as it relates to names or titles

    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
    ħĭ
    -0.99
    éĹĺ
    -0.95
     Carbuncle
    -0.81
    æ©Ł
    -0.81
    ¥µ
    -0.80
    OME
    -0.78
    ģĸ
    -0.77
    æĸ¹
    -0.77
    ARDS
    -0.76
    士
    -0.74
    POSITIVE LOGITS
    agraph
    1.28
    allel
    1.12
    liament
    1.11
    anoia
    1.10
    vati
    1.03
    amount
    0.94
    abolic
    0.89
    anthrop
    0.89
    alysis
    0.88
    cells
    0.88
    Activations Density 0.010%

    No Known Activations