© 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. 19420
    Prev
    Next
    INDEX
    Explanations

    actions or intents related to attempting or striving for something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "trying."

    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
    otor
    -0.62
    dylib
    -0.60
    requisite
    -0.58
    inth
    -0.56
    ahu
    -0.55
    oola
    -0.54
    ainers
    -0.53
    krit
    -0.53
    chnology
    -0.52
    eria
    -0.52
    POSITIVE LOGITS
     desperately
    1.12
     to
    1.12
     unsuccessfully
    1.00
     harder
    0.95
     valiant
    0.93
     hard
    0.87
     frantically
    0.82
     vain
    0.81
    to
    0.74
     tirelessly
    0.71
    Activations Density 0.057%

    No Known Activations