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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 5318
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "to go to" followed by a location or destination

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heast
    -0.67
    selves
    -0.67
     compounded
    -0.66
    nav
    -0.65
     netted
    -0.63
    etheless
    -0.62
     graz
    -0.62
    emort
    -0.61
    cape
    -0.61
     transmitted
    -0.60
    POSITIVE LOGITS
     bed
    0.85
    pless
    0.82
     sleep
    0.81
     extremes
    0.80
     jail
    0.78
     concerts
    0.69
     grips
    0.68
     hell
    0.68
    ying
    0.67
    ALK
    0.67
    Activations Density 0.103%

    No Known Activations