© 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. 8-RES-JB
    11. 22270
    Prev
    Next
    INDEX
    Explanations

    scientific studies and research-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to studies and research findings

    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
     kisses
    -0.77
     Celt
    -0.73
     goodbye
    -0.72
     toast
    -0.68
     Chili
    -0.68
     Cot
    -0.66
    zz
    -0.66
     ceremony
    -0.64
     hugs
    -0.64
    Happy
    -0.63
    POSITIVE LOGITS
     conducted
    1.21
     evaluating
    1.08
    uggest
    1.06
     examining
    1.03
     documenting
    1.01
     analyzing
    1.00
     published
    1.00
    published
    1.00
     analyzed
    0.98
     studies
    0.96
    Activations Density 0.349%

    No Known Activations