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. 8-RES-JB
    6. 22733
    Prev
    Next
    INDEX
    Explanations

    keywords related to the purpose or intent of something

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of purpose

    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
    thumbnails
    -0.69
     weeds
    -0.67
    alus
    -0.64
    culosis
    -0.62
     varieties
    -0.62
     Leopard
    -0.60
     giants
    -0.60
    MX
    -0.60
     Toad
    -0.60
     Isles
    -0.59
    POSITIVE LOGITS
    ful
    1.36
    fully
    1.12
    lessly
    1.09
    fulness
    1.04
    lessness
    0.98
    FUL
    0.92
    teness
    0.86
    tenance
    0.85
    ality
    0.82
    bringer
    0.82
    Activations Density 0.037%

    No Known Activations