© 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. 17613
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with durations (time or percentage) and possibly accompanying actions or states

    oai_token-act-pair · gpt-3.5-turbo

    quantitative information related to durations and prevalence

    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
     Vote
    -0.83
    çīĪ
    -0.79
     Alphabet
    -0.67
    Vote
    -0.67
     bidding
    -0.66
     Indie
    -0.65
     spoiler
    -0.65
     Bib
    -0.64
    UGC
    -0.64
     Revenue
    -0.64
    POSITIVE LOGITS
     symptoms
    1.20
     Symptoms
    1.14
     lasting
    1.09
    Sym
    1.08
     onset
    1.05
     remission
    1.03
     dosage
    1.02
     physiological
    1.02
     lesions
    1.02
    ptoms
    1.01
    Activations Density 0.299%

    No Known Activations