© 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. 10-RES-JB
    11. 2287
    Prev
    Next
    INDEX
    Explanations

    the name "Raj" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Raj."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¦
    -0.63
    ancial
    -0.61
    tein
    -0.61
     positives
    -0.59
     precisely
    -0.59
    ABLE
    -0.58
    bsite
    -0.57
     Liberia
    -0.56
     Sounders
    -0.56
     solvent
    -0.55
    POSITIVE LOGITS
    arat
    1.25
    aram
    1.10
    endra
    1.07
    rang
    1.03
    ataka
    0.98
    ahar
    0.95
    hari
    0.92
    olla
    0.89
    deep
    0.89
    esh
    0.89
    Activations Density 0.026%

    No Known Activations