© 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. 0-RES-JB
    11. 22237
    Prev
    Next
    INDEX
    Explanations

    details about incidents or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "happened."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    limit
    -0.56
    isons
    -0.55
     Optim
    -0.54
    cul
    -0.54
    sts
    -0.53
     ratings
    -0.53
     firm
    -0.53
     Pra
    -0.52
     full
    -0.51
     Temper
    -0.51
    POSITIVE LOGITS
     happened
    3.52
     happens
    2.57
     occurred
    2.43
     transpired
    2.38
     happen
    2.23
     happ
    2.18
     happening
    1.79
     occurs
    1.72
     unfolded
    1.59
     Happ
    1.56
    Activations Density 0.019%

    No Known Activations