© 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. 4-RES-JB
    11. 8559
    Prev
    Next
    INDEX
    Explanations

    formatting or punctuation marks, especially periods

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and percentages

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

    No Comments

    Negative Logits
     advis
    -0.76
     sustainability
    -0.75
     behavi
    -0.75
     withd
    -0.74
     homelessness
    -0.73
     chained
    -0.73
     overflow
    -0.73
     undermin
    -0.72
     independ
    -0.72
     proactive
    -0.71
    POSITIVE LOGITS
    htm
    1.15
    jpg
    1.14
    Downloadha
    1.12
    sbm
    1.10
    html
    1.04
    5
    1.01
    txt
    1.01
     Retrieved
    0.98
    png
    0.96
    jar
    0.91
    Activations Density 0.226%

    No Known Activations