© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 17411
    Prev
    Next
    INDEX
    Explanations

    phrases related to questions or actions starting with 'Can'

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "Can."

    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
     Confeder
    -0.69
     rehears
    -0.60
     striving
    -0.57
     reven
    -0.57
     wanting
    -0.55
    eering
    -0.55
     starring
    -0.54
     presentation
    -0.54
     aven
    -0.54
     wart
    -0.54
    POSITIVE LOGITS
    't
    1.63
    berra
    1.46
    adian
    1.43
    vas
    1.38
    opy
    1.23
    isters
    1.16
    ister
    1.12
    nery
    1.06
    ny
    1.02
    ibal
    1.02
    Activations Density 0.069%

    No Known Activations