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. 3205
    Prev
    Next
    INDEX
    Explanations

    phrases related to philosophy and society

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts, indicating relationships or connections between ideas

    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
    DragonMagazine
    -0.75
    EMS
    -0.70
    aws
    -0.67
    ATS
    -0.65
    ETS
    -0.64
    visual
    -0.64
    CF
    -0.64
    sbm
    -0.63
    dayName
    -0.63
    ILS
    -0.63
    POSITIVE LOGITS
     thereby
    1.17
     therefore
    1.16
     consequently
    1.12
     thus
    1.12
     hence
    1.10
     vice
    0.88
     consequ
    0.88
     thence
    0.86
     furthermore
    0.85
     moreover
    0.84
    Activations Density 0.503%

    No Known Activations