© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 12235
    Prev
    Next
    INDEX
    Explanations

    negations or refusals

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a lack or absence of something

    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
    leaning
    -0.70
    amazon
    -0.68
    qua
    -0.68
    xtap
    -0.68
    FIG
    -0.67
    Wave
    -0.64
    Media
    -0.63
    println
    -0.62
    interstitial
    -0.62
    ale
    -0.62
    POSITIVE LOGITS
     clue
    1.38
     idea
    1.31
     intention
    1.28
     qual
    1.19
     illusions
    1.17
     recollection
    1.12
     doubt
    1.09
     intentions
    1.08
     inclination
    1.07
     objection
    1.07
    Activations Density 0.061%

    No Known Activations