© 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. 9-RES-JB
    6. 2944
    Prev
    Next
    INDEX
    Explanations

    words related to decision-making and preferences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "or."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tackle
    -0.72
    mostly
    -0.66
    now
    -0.58
    then
    -0.56
     Monsters
    -0.56
    probably
    -0.54
     Field
    -0.54
    URA
    -0.54
    leted
    -0.53
    idem
    -0.53
    POSITIVE LOGITS
     anything
    1.39
    chard
    1.11
    nam
    1.11
     whatsoever
    1.07
     any
    1.06
    acles
    1.03
     anymore
    1.03
     else
    1.01
    Else
    1.00
     anywhere
    0.99
    Activations Density 0.120%

    No Known Activations