© 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. 9-RES-JB
    11. 18109
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "can"

    oai_token-act-pair · gpt-3.5-turbo

    the term "Can" or variations of it, indicating a focus on capabilities or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Confeder
    -0.71
     Reich
    -0.67
     striving
    -0.60
     reven
    -0.60
    eering
    -0.60
     rehears
    -0.59
     aven
    -0.57
    é¾įå¥ij士
    -0.57
     dwar
    -0.56
     rehearsal
    -0.55
    POSITIVE LOGITS
    't
    1.49
    berra
    1.41
    adian
    1.39
    vas
    1.30
    isters
    1.23
    opy
    1.14
    ister
    1.13
    nery
    1.05
    ibal
    1.01
    adas
    0.99
    Activations Density 0.077%

    No Known Activations