© 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. 2644
    Prev
    Next
    INDEX
    Explanations

    mentions of political or economic topics

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation marks and statements of opinion or commentary

    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
     rele
    -0.81
    iencies
    -0.79
    »Ĵ
    -0.77
     reinvest
    -0.75
    awaru
    -0.72
     barg
    -0.72
     manageable
    -0.71
    finished
    -0.70
    ĪĴ
    -0.70
     servicing
    -0.70
    POSITIVE LOGITS
     Others
    1.34
    Others
    1.19
     They
    1.14
     Some
    1.09
     Critics
    1.06
     Several
    1.05
     Their
    1.01
     Speaking
    0.99
     Advoc
    0.98
     Analyst
    0.97
    Activations Density 0.343%

    No Known Activations