© 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. 7-RES-JB
    11. 9805
    Prev
    Next
    INDEX
    Explanations

    phrases that begin with the word "Or."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Or" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arthed
    -0.70
    UD
    -0.69
    Material
    -0.67
    "}],"
    -0.67
    FACE
    -0.66
    owner
    -0.66
    ocratic
    -0.66
    estro
    -0.65
    ocracy
    -0.64
     âĢİ
    -0.64
    POSITIVE LOGITS
    thodox
    1.21
     alternatively
    1.16
    phans
    1.14
    phan
    1.08
    acular
    1.07
    lando
    1.05
    chard
    0.97
    Else
    0.96
     maybe
    0.94
     worse
    0.88
    Activations Density 0.036%

    No Known Activations