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. 11-RES-JB
    6. 20000
    Prev
    Next
    INDEX
    Explanations

    positive and negative adjectives and nouns related to various visual and sensory aspects

    oai_token-act-pair · gpt-3.5-turbo

    negative qualities or criticisms related to various subjects or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gdala
    -0.85
    hower
    -0.78
    yip
    -0.77
    cellent
    -0.74
    Enabled
    -0.72
    ilege
    -0.71
    cture
    -0.71
    trak
    -0.71
    qqa
    -0.69
    ajor
    -0.69
    POSITIVE LOGITS
    nesses
    1.01
     lifestyles
    1.00
     punishments
    1.00
     layouts
    0.99
     diets
    0.98
     deadlines
    0.97
     schedules
    0.97
     personalities
    0.96
     setups
    0.92
     environments
    0.92
    Activations Density 0.226%

    No Known Activations