© 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. 2898
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of difference or variability

    oai_token-act-pair · gpt-3.5-turbo

    discussions about differing perspectives or experiences

    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
     Roose
    -0.82
    media
    -0.74
    IED
    -0.72
     Sidney
    -0.69
    TED
    -0.69
    BILL
    -0.67
     Ezek
    -0.66
    redited
    -0.65
    Video
    -0.65
     Podesta
    -0.64
    POSITIVE LOGITS
     differing
    1.37
     differences
    1.29
     variability
    1.23
     variation
    1.22
     variations
    1.20
     distinctions
    1.18
     varying
    1.18
     uniqueness
    1.16
     different
    1.14
    different
    1.11
    Activations Density 0.923%

    No Known Activations