© 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. 10664
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "quote."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "note."

    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
    £ı
    -0.80
    Ļ½
    -0.74
    hips
    -0.71
    owship
    -0.70
    antha
    -0.67
    ruary
    -0.67
    ounced
    -0.65
     disapp
    -0.65
    maxwell
    -0.63
    «ĺ
    -0.63
    POSITIVE LOGITS
    OPLE
    1.08
    lete
    1.02
    chn
    1.00
    chnology
    0.98
    ague
    0.95
    tsky
    0.92
    vice
    0.92
    zzi
    0.91
    ptic
    0.86
    onga
    0.85
    Activations Density 0.022%

    No Known Activations