© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17314
    Prev
    Next
    INDEX
    Explanations

    information related to contracts, agreements, and expiration dates

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to contracts and contract durations in sports

    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
     eyewitness
    -0.79
    »Ĵ
    -0.75
     bystanders
    -0.68
     spores
    -0.66
     subtle
    -0.66
     contam
    -0.65
     sightings
    -0.65
     passers
    -0.64
     Hast
    -0.63
     mole
    -0.63
    POSITIVE LOGITS
     expires
    1.48
     expire
    1.36
     expired
    1.25
     2019
    1.18
     2021
    1.15
    2019
    1.05
     2018
    1.04
     2022
    1.03
     terminate
    0.99
     2024
    0.98
    Activations Density 0.249%

    No Known Activations