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. 11186
    Prev
    Next
    INDEX
    Explanations

    phrases indicating additional information or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    phrases or concepts indicating caveats or additional notes

    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
    twitch
    -0.75
    Constructed
    -0.74
    hard
    -0.66
    sil
    -0.64
    arij
    -0.63
    spot
    -0.62
    isf
    -0.60
    shell
    -0.59
    iminary
    -0.59
    ophys
    -0.59
    POSITIVE LOGITS
    lihood
    0.81
    epad
    0.68
    _>
    0.64
     mentioning
    0.64
     indexes
    0.63
    omsday
    0.63
    DonaldTrump
    0.62
     incidentally
    0.60
     è£ı
    0.60
     imagine
    0.59
    Activations Density 0.022%

    No Known Activations