Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 9710
    Prev
    Next
    INDEX
    Explanations

    words related to transportation and movement, specifically boarding and disembarking activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "boarded" and related actions of boarding or disembarking from transportation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atorial
    -0.78
    adal
    -0.76
    nexus
    -0.76
    izes
    -0.75
    itar
    -0.67
    ensing
    -0.66
    amount
    -0.65
    nesota
    -0.65
    MS
    -0.63
    ensed
    -0.63
    POSITIVE LOGITS
     boarded
    1.18
    folios
    0.98
    ĵĺ
    0.92
    deck
    0.85
    mast
    0.78
    escription
    0.76
     sail
    0.70
     Yamato
    0.68
    ||||
    0.67
    veyard
    0.67
    Activations Density 0.009%

    No Known Activations