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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 17325
    Prev
    Next
    INDEX
    Explanations

    trick-related words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    variations of the term "trick."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    manship
    -0.84
     Mechdragon
    -0.77
     Grande
    -0.75
    ELS
    -0.70
     Flake
    -0.68
    heid
    -0.67
     yeast
    -0.65
    ãģ®éŃĶ
    -0.64
     arts
    -0.63
     doubling
    -0.61
    POSITIVE LOGITS
    ainer
    1.37
    acker
    1.19
    ains
    1.17
    udeau
    1.16
    ading
    1.11
    umps
    1.09
    ained
    1.08
    acking
    1.08
    ickle
    1.08
    ader
    1.07
    Activations Density 0.023%

    No Known Activations