© 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. 11-RES-JB
    6. 23256
    Prev
    Next
    INDEX
    Explanations

    consecutive occurrences of the word "no" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    negations present in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stard
    -0.59
    aukee
    -0.56
     Latest
    -0.54
     externalToEVAOnly
    -0.54
     Pioneer
    -0.53
     Rend
    -0.53
    theless
    -0.52
     Polaris
    -0.52
     Converted
    -0.52
    edIn
    -0.52
    POSITIVE LOGITS
    xious
    1.27
    otropic
    1.03
    va
    1.02
    ogie
    1.00
    vell
    0.98
    ct
    0.97
    ve
    0.96
    otrop
    0.96
    ose
    0.95
    vel
    0.92
    Activations Density 0.038%

    No Known Activations