© 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. 11-RES-JB
    11. 9089
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to brain studies

    oai_token-act-pair · gpt-3.5-turbo

    scientific terms related to cardiovascular health and biochemical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    source
    -0.75
    isSpecialOrderable
    -0.70
    ento
    -0.67
    ilies
    -0.66
    indust
    -0.66
    ertain
    -0.64
    cest
    -0.64
    BuyableInstoreAndOnline
    -0.64
    foreseen
    -0.63
    meaning
    -0.63
    POSITIVE LOGITS
     mRNA
    1.19
     biomark
    1.17
     serum
    1.10
     metabolites
    1.10
     markers
    1.05
     normalized
    1.00
     scores
    0.99
     amplitude
    0.97
     cortisol
    0.96
     concentrations
    0.96
    Activations Density 0.199%

    No Known Activations