© 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. 9927
    Prev
    Next
    INDEX
    Explanations

    electric signals or computer code

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters that appear frequently, indicating possible formatting or coding issues

    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
     mate
    -0.67
     Voyager
    -0.67
     dispers
    -0.66
     Belg
    -0.66
     polyg
    -0.65
     interf
    -0.63
     Jem
    -0.62
     handshake
    -0.60
     concentrate
    -0.59
     technique
    -0.59
    POSITIVE LOGITS
    ª
    1.44
    ¡
    1.29
    ¹
    1.26
    Ļ
    1.23
    Į
    1.22
    Ŀ
    1.21
    ¤
    1.21
    ı
    1.20
    Ń
    1.18
    ¬
    1.18
    Activations Density 0.109%

    No Known Activations