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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 16502
    Prev
    Next
    INDEX
    Explanations

    words related to emotional or physical support

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with positive support, assurance, and well-being

    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
    otine
    -0.62
     Mile
    -0.59
    osphere
    -0.58
     thing
    -0.57
    ograph
    -0.53
     outing
    -0.53
     smoker
    -0.52
     choir
    -0.52
     metic
    -0.51
     Goldberg
    -0.51
    POSITIVE LOGITS
    fully
    0.81
    DragonMagazine
    0.75
    iless
    0.75
    ifully
    0.73
    ively
    0.71
    aterasu
    0.66
    âĨij
    0.66
    tips
    0.65
    luaj
    0.65
    trump
    0.64
    Activations Density 0.309%

    No Known Activations