© 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. 10242
    Prev
    Next
    INDEX
    Explanations

    texts written in a specific foreign language

    oai_token-act-pair · gpt-3.5-turbo

    characters and symbols from various encoded scripts

    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
    espie
    -0.94
     womb
    -0.68
    ttes
    -0.67
     Murdoch
    -0.67
     treasury
    -0.66
     Treasury
    -0.66
     PD
    -0.64
    enegger
    -0.63
     Coulter
    -0.63
     Wink
    -0.62
    POSITIVE LOGITS
    ï¸ı
    1.08
    Ô
    1.03
    âĪ
    0.99
    ðĿ
    0.87
    ãĥ©ãĥ³
    0.86
    Ì
    0.85
    £
    0.85
    Æ
    0.85
    Ëľ
    0.84
    в
    0.84
    Activations Density 0.047%

    No Known Activations