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. 8-RES-JB
    6. 15536
    Prev
    Next
    INDEX
    Explanations

    sentences relating to actions and activities being done by people

    oai_token-act-pair · gpt-3.5-turbo

    dialogue and interactions between characters

    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
    ortium
    -0.60
    ador
    -0.59
     disadvantages
    -0.59
    -)
    -0.58
    andra
    -0.56
     hindsight
    -0.55
     centr
    -0.54
     disadvantage
    -0.54
     disagrees
    -0.54
     nowadays
    -0.54
    POSITIVE LOGITS
    FIR
    0.64
     accordingly
    0.64
     proceeded
    0.60
     prest
    0.60
    SPONSORED
    0.59
    oka
    0.59
    ãĤ©
    0.59
    ãĥŃ
    0.58
    hid
    0.57
    hello
    0.56
    Activations Density 0.655%

    No Known Activations