© 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. 1-RES-JB
    6. 2111
    Prev
    Next
    INDEX
    Explanations

    instances of the word "tot" or similar variations like "totem", "totality", or "Higgins"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "tot" and related terms, as well as references to specific entities like "Pastebin" and "Guth."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cers
    -0.73
     incent
    -0.72
    ctions
    -0.67
    cer
    -0.67
    ļéĨĴ
    -0.63
     banker
    -0.62
    operator
    -0.61
    fol
    -0.59
    ayne
    -0.59
    Kh
    -0.57
    POSITIVE LOGITS
     Tot
    1.15
     tot
    0.99
    ems
    0.98
    enhagen
    0.85
    owa
    0.85
    ogle
    0.84
    zzi
    0.79
    etting
    0.79
    ebin
    0.77
    aken
    0.77
    Activations Density 0.014%

    No Known Activations