© 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. 13523
    Prev
    Next
    INDEX
    Explanations

    superlatives and comparisons emphasizing extremity

    oai_token-act-pair · gpt-3.5-turbo

    quantifiers that indicate extremes or comparisons

    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
    ————
    -0.85
    ĺħ
    -0.80
    potion
    -0.79
    reating
    -0.70
    ————————
    -0.70
    ugi
    -0.68
    module
    -0.68
    Camp
    -0.66
    asus
    -0.65
    along
    -0.65
    POSITIVE LOGITS
     slightest
    1.15
     smallest
    1.10
     curs
    0.91
     simplest
    0.87
     superf
    0.87
     mundane
    0.87
     watered
    0.83
     lowly
    0.81
     modest
    0.81
     moderately
    0.80
    Activations Density 0.095%

    No Known Activations