© 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. 3098
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and sentence-ending structures in the text

    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
     affili
    -1.00
     hires
    -0.91
    jriwal
    -0.86
     discrim
    -0.85
     divest
    -0.85
     negoti
    -0.84
     licensing
    -0.81
     associations
    -0.80
     yearly
    -0.80
     categor
    -0.80
    POSITIVE LOGITS
     Afterwards
    1.16
     Seconds
    1.09
     Minutes
    1.05
     Moments
    1.03
    Jordan
    1.02
    Mom
    0.96
    Match
    0.92
    Shortly
    0.90
    After
    0.90
    Mid
    0.89
    Activations Density 0.170%

    No Known Activations