© 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. 8016
    Prev
    Next
    INDEX
    Explanations

    words related to changes and announcements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate changes or modifications being implemented

    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
     quiz
    -0.68
     answ
    -0.66
     Noir
    -0.64
     brood
    -0.64
    ا
    -0.63
     Hath
    -0.63
     Duchess
    -0.62
     Faul
    -0.61
     hung
    -0.60
    essor
    -0.60
    POSITIVE LOGITS
     effected
    1.21
     gradual
    1.12
     drastic
    1.11
     incremental
    1.03
     occurring
    1.03
     noticeable
    0.99
     occur
    0.98
     affecting
    0.97
     occurred
    0.96
     happening
    0.95
    Activations Density 0.325%

    No Known Activations