© 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. 4-RES-JB
    6. 24268
    Prev
    Next
    INDEX
    Explanations

    words related to categorization or scrutiny

    oai_token-act-pair · gpt-3.5-turbo

    terms related to categorization, harmony, and scrutiny

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

    No Comments

    Negative Logits
    quickShipAvailable
    -0.74
    avorite
    -0.70
     Madison
    -0.64
     Uri
    -0.64
    yip
    -0.64
     Venice
    -0.63
    HOME
    -0.62
     Elves
    -0.62
     Promise
    -0.62
     Viking
    -0.61
    POSITIVE LOGITS
    ically
    1.48
    izing
    1.45
    ized
    1.44
    ised
    1.38
    izers
    1.36
    ization
    1.29
    ising
    1.29
    izations
    1.26
    izer
    1.23
    ics
    1.22
    Activations Density 0.036%

    No Known Activations