© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10047
    Prev
    Next
    INDEX
    Explanations

    names or terms emphasizing importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    instances of absence and presence in context

    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
    roit
    -0.63
     \'
    -0.59
    liv
    -0.59
     tempered
    -0.57
    Narr
    -0.57
    nih
    -0.56
     unequ
    -0.54
    heid
    -0.52
    ternity
    -0.52
    ãĥ´ãĤ¡
    -0.52
    POSITIVE LOGITS
     is
    1.06
     are
    0.94
     was
    0.87
     involves
    0.81
     include
    0.70
     relates
    0.68
     were
    0.68
     lies
    0.65
     Is
    0.64
    is
    0.63
    Activations Density 0.690%

    No Known Activations