© 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. 0-RES-JB
    6. 6545
    Prev
    Next
    INDEX
    Explanations

    phrases related to a complete set or whole situation

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "entire" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kr
    -0.61
    âĢij
    -0.58
    ciplinary
    -0.58
    giving
    -0.57
    /(
    -0.56
    NB
    -0.55
    aire
    -0.54
     Guardiola
    -0.54
    nr
    -0.53
    ben
    -0.53
    POSITIVE LOGITS
     entire
    3.64
     whole
    2.67
     entirety
    2.57
     ENT
    1.50
     remainder
    1.22
     vast
    1.20
     Whole
    1.15
     actual
    1.14
     entirely
    1.13
     full
    1.03
    Activations Density 0.013%

    No Known Activations