© 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. 11-RES-JB
    11. 6980
    Prev
    Next
    INDEX
    Explanations

    numbers, codes, and technical terms

    oai_token-act-pair · gpt-3.5-turbo

    specific identifiers, codes, or references related to data and statistics

    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
    én
    -0.71
     HSBC
    -0.70
     astroph
    -0.70
     diagn
    -0.69
     Penny
    -0.68
     Fay
    -0.67
     Hak
    -0.67
     EMP
    -0.66
     Fif
    -0.65
     Ash
    -0.64
    POSITIVE LOGITS
    2
    1.38
     2
    1.19
    ãĤ°
    0.96
    2200
    0.94
    ²
    0.92
    002
    0.91
    two
    0.89
     II
    0.89
    02
    0.88
    II
    0.85
    Activations Density 0.222%

    No Known Activations