Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 17470
    Prev
    Next
    INDEX
    Explanations

    names or references related to individuals, possibly of Arabic origin

    oai_token-act-pair · gpt-3.5-turbo

    the name "Annani" and variations of that name

    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
    xual
    -0.76
     compe
    -0.67
     Ãľ
    -0.63
    EStream
    -0.63
     caution
    -0.63
     welf
    -0.62
     acron
    -0.62
     CLSID
    -0.62
     mosqu
    -0.61
     BALL
    -0.58
    POSITIVE LOGITS
    ihil
    1.18
    uggets
    1.13
    aturally
    1.12
    onsense
    1.12
    umerous
    1.08
    ucle
    1.08
    ovation
    1.08
    orthern
    1.01
    imble
    1.00
    umeric
    0.99
    Activations Density 0.040%

    No Known Activations