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. 5-RES-JB
    6. 20642
    Prev
    Next
    INDEX
    Explanations

    phrases related to movement or change of location

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating movement or returning to a place

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceFile
    -0.68
    Storage
    -0.65
    Applic
    -0.63
    pmwiki
    -0.63
    conn
    -0.62
    Discuss
    -0.62
    channelAvailability
    -0.61
     unden
    -0.60
     Annotations
    -0.59
    abulary
    -0.59
    POSITIVE LOGITS
     blows
    0.73
     fray
    0.72
    arse
    0.71
    acht
    0.71
     smelling
    0.70
     swinging
    0.67
    razil
    0.67
    riots
    0.66
    arent
    0.64
    redit
    0.63
    Activations Density 0.073%

    No Known Activations