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. 7-RES-JB
    6. 10379
    Prev
    Next
    INDEX
    Explanations

    communication-related actions, such as sending messages or letters

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of communication and messaging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hispanic
    -0.71
    artifacts
    -0.67
    CENT
    -0.67
    PRESS
    -0.62
     suicides
    -0.60
     Fog
    -0.59
    llah
    -0.59
    urate
    -0.57
     Congress
    -0.57
     Cth
    -0.57
    POSITIVE LOGITS
    ãĥīãĥ©ãĤ´ãĥ³
    0.81
     opportunity
    0.69
    ãĥ¥
    0.68
    ãĤ¹ãĥĪ
    0.66
    andon
    0.65
     chance
    0.64
    ansom
    0.64
    EngineDebug
    0.63
     coveted
    0.63
     priceless
    0.63
    Activations Density 0.205%

    No Known Activations