© 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. 10-RES-JB
    6. 13618
    Prev
    Next
    INDEX
    Explanations

    year references

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and references to specific years or notable events

    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
    enture
    -0.73
     incent
    -0.65
    scan
    -0.61
    redients
    -0.61
    wcs
    -0.61
     females
    -0.60
     purse
    -0.58
     women
    -0.58
     parity
    -0.58
     equivalents
    -0.57
    POSITIVE LOGITS
    Mr
    1.26
    His
    1.22
     Mr
    1.18
    He
    1.15
     Manziel
    1.14
     Jaune
    1.10
     he
    1.08
     He
    1.07
     Duterte
    1.05
     Rahul
    1.05
    Activations Density 1.074%

    No Known Activations