© 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. 10-RES-JB
    11. 2759
    Prev
    Next
    INDEX
    Explanations

    hyphenated words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating negation or absence

    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
     Ake
    -0.71
     Seeking
    -0.69
     Pok
    -0.68
     fade
    -0.68
     harshly
    -0.68
     moder
    -0.68
     Tik
    -0.65
     Levi
    -0.65
     geared
    -0.65
     cultiv
    -0.65
    POSITIVE LOGITS
    same
    1.27
    middle
    1.21
    mom
    1.20
    money
    1.16
    grain
    1.14
    scenes
    1.14
    prem
    1.14
    distance
    1.14
    surface
    1.12
    ground
    1.11
    Activations Density 0.020%

    No Known Activations