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. 6-RES-JB
    6. 8110
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to preparation, planning, or deliberation

    oai_token-act-pair · gpt-3.5-turbo

    words and terms related to premeditation or planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lago
    -0.78
     Woodward
    -0.68
    Lens
    -0.66
    =-=-=-=-=-=-=-=-
    -0.65
    ãĥīãĥ©ãĤ´ãĥ³
    -0.63
     independents
    -0.63
     dissatisf
    -0.63
     realism
    -0.62
    ONSORED
    -0.61
     inconsistency
    -0.61
    POSITIVE LOGITS
    atural
    0.94
    emption
    0.93
    atal
    0.89
    empt
    0.87
    aturally
    0.82
    autions
    0.80
    aphael
    0.80
    atives
    0.80
    ition
    0.78
    ptive
    0.77
    Activations Density 0.048%

    No Known Activations