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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 2837
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking actions or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ieth
    -0.71
    meet
    -0.69
    ĨĴ
    -0.69
     Citizen
    -0.68
    DEN
    -0.68
    Boss
    -0.67
    ody
    -0.67
    onica
    -0.67
    ern
    -0.64
    agos
    -0.64
    POSITIVE LOGITS
     shove
    1.14
     toss
    1.03
     put
    0.98
     THEN
    0.97
     vo
    0.93
     threw
    0.92
     then
    0.90
     convert
    0.89
     paste
    0.89
     spit
    0.88
    Activations Density 0.167%

    No Known Activations