© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 7863
    Prev
    Next
    INDEX
    Explanations

    phrases indicating importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    references to significant concepts or ideas within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortex
    -0.86
     Telecommunications
    -0.74
    DOS
    -0.71
    oise
    -0.68
    de
    -0.67
    ilt
    -0.67
    ardless
    -0.66
    igon
    -0.66
    ilver
    -0.64
    mast
    -0.63
    POSITIVE LOGITS
     else
    1.33
    Else
    1.17
     akin
    0.91
     unheard
    0.88
     Else
    0.83
     intangible
    0.81
     shameful
    0.80
     unimaginable
    0.78
     unusual
    0.78
     uncommon
    0.76
    Activations Density 0.041%

    No Known Activations