© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 17373
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating the lowest degree or level

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote the concept of "least" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raltar
    -0.72
    zie
    -0.67
    anism
    -0.67
    still
    -0.67
    £ı
    -0.66
    andise
    -0.64
    çīĪ
    -0.64
    wark
    -0.63
     conclud
    -0.61
    éĸ
    -0.61
    POSITIVE LOGITS
     amount
    0.97
     bit
    0.97
     intrusive
    0.96
     restrictive
    0.96
     expensive
    0.87
     desirable
    0.87
     objectionable
    0.85
     invasive
    0.80
     favourable
    0.78
    expensive
    0.76
    Activations Density 0.030%

    No Known Activations