© 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. 10-RES-JB
    11. 735
    Prev
    Next
    INDEX
    Explanations

    superlatives indicating proximity or similarity

    oai_token-act-pair · gpt-3.5-turbo

    references to things that are described as "closest" or the most comparable to a given subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anity
    -0.80
    anners
    -0.79
    inous
    -0.76
    _-
    -0.76
    ilts
    -0.70
    ãĤ¡
    -0.67
    uct
    -0.67
    tons
    -0.66
    ãĥīãĥ©
    -0.66
    DOM
    -0.64
    POSITIVE LOGITS
     approximation
    1.08
     resemblance
    1.01
     thing
    0.95
     analogue
    0.95
     comparable
    0.86
     proximity
    0.85
     approximate
    0.85
     closest
    0.82
     approx
    0.82
     comparison
    0.79
    Activations Density 0.046%

    No Known Activations