© 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. 17903
    Prev
    Next
    INDEX
    Explanations

    names or references related to a specific person named "Pritviraj"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals named "Aj" or similar variants

    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
     Lange
    -0.67
     SEA
    -0.66
     diffusion
    -0.64
     diffuse
    -0.63
     grounds
    -0.62
     flock
    -0.61
     steril
    -0.61
     gle
    -0.60
     liner
    -0.59
     herds
    -0.59
    POSITIVE LOGITS
    aj
    4.25
    aja
    2.03
    ajo
    1.95
    oj
    1.61
    aji
    1.39
    ij
    1.26
    amar
    1.25
    uj
    1.24
    az
    1.23
    aw
    1.18
    Activations Density 0.020%

    No Known Activations