© 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. 9-RES-JB
    11. 15401
    Prev
    Next
    INDEX
    Explanations

    economic and financial terms

    oai_token-act-pair · gpt-3.5-turbo

    economic and political metrics or indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.71
    DragonMagazine
    -0.62
    zbek
    -0.62
    ĪĴ
    -0.58
    £ı
    -0.58
     actionGroup
    -0.57
    EStreamFrame
    -0.56
    itialized
    -0.55
    Examples
    -0.54
    ropolitan
    -0.53
    POSITIVE LOGITS
     considerably
    1.28
     immensely
    1.22
     tremendously
    1.22
     enormously
    1.16
     altogether
    0.99
     exponentially
    0.98
     significantly
    0.97
     greatly
    0.96
     substantially
    0.91
     dearly
    0.90
    Activations Density 0.612%

    No Known Activations