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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 343
    Prev
    Next
    INDEX
    Explanations

    names or terms related to someone named Adel

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Adel" and its variations

    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
    boys
    -0.73
     RIS
    -0.73
    LOCK
    -0.72
     TIM
    -0.69
     luck
    -0.68
    ELS
    -0.65
    ZZ
    -0.63
    LR
    -0.63
     Bye
    -0.63
     WHITE
    -0.62
    POSITIVE LOGITS
    adel
    1.18
    anguage
    1.06
    oad
    1.03
    oaded
    0.93
    icate
    0.86
    ics
    0.85
    inking
    0.85
    ications
    0.83
    anie
    0.83
    indal
    0.81
    Activations Density 0.016%

    No Known Activations