© 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. 11738
    Prev
    Next
    INDEX
    Explanations

    negations or exceptions in statements

    oai_token-act-pair · gpt-3.5-turbo

    negations or instances of the word "not."

    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
     contention
    -0.64
    ãģ®ç
    -0.60
    ixel
    -0.59
     Circuit
    -0.58
     Alleg
    -0.58
     Pratt
    -0.57
    stakes
    -0.57
     vows
    -0.57
     Spotlight
    -0.56
     Kry
    -0.56
    POSITIVE LOGITS
    icably
    1.35
     necessarily
    1.23
    epad
    1.09
    icable
    1.04
    hin
    0.98
    orious
    0.98
    withstanding
    0.97
    ifications
    0.92
    ional
    0.92
    ices
    0.92
    Activations Density 0.158%

    No Known Activations