© 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. 7-RES-JB
    11. 21530
    Prev
    Next
    INDEX
    Explanations

    mentions where events or circumstances are unexpectedly occurring, or pointing out unique characteristics of people or objects

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "happened to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aina
    -0.75
    sett
    -0.73
    chlor
    -0.70
    Reviewed
    -0.69
    itized
    -0.69
    Font
    -0.69
    anooga
    -0.65
     canopy
    -0.63
     assurance
    -0.62
    ighting
    -0.62
    POSITIVE LOGITS
     coincide
    1.25
     resemble
    0.91
     belong
    0.87
     introduce
    0.83
     recognise
    0.80
     reside
    0.79
     satisfy
    0.75
     mention
    0.75
     meet
    0.71
     collide
    0.70
    Activations Density 0.044%

    No Known Activations