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. 22415
    Prev
    Next
    INDEX
    Explanations

    references to long-lasting impacts or influences, often of historical or cultural significance

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "legacy."

    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
    owler
    -0.77
    tics
    -0.77
    acus
    -0.75
    anooga
    -0.74
    ramid
    -0.74
    bians
    -0.73
    earcher
    -0.71
    aber
    -0.71
    kers
    -0.70
    aleigh
    -0.69
    POSITIVE LOGITS
     legacy
    1.08
     Legacy
    0.77
     baggage
    0.77
    stones
    0.73
    arily
    0.71
    lore
    0.69
     bearer
    0.68
     writ
    0.65
    emonic
    0.65
     ingrained
    0.64
    Activations Density 0.022%

    No Known Activations