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. 2-RES-JB
    6. 8672
    Prev
    Next
    INDEX
    Explanations

    words related to the town of Bunkerville

    oai_token-act-pair · gpt-3.5-turbo

    instances of the "unk" token, which likely indicates missing or unrecognized information in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     expressive
    -0.66
     sunshine
    -0.64
    ggle
    -0.64
     latitude
    -0.62
     climates
    -0.61
    voy
    -0.61
     disobedience
    -0.60
     hor
    -0.59
     gown
    -0.58
     remarkable
    -0.58
    POSITIVE LOGITS
    unk
    1.11
    buster
    0.91
    lift
    0.88
    etsu
    0.88
    geon
    0.87
    unks
    0.86
    regate
    0.86
    ernel
    0.81
    utsche
    0.78
    ELF
    0.78
    Activations Density 0.008%

    No Known Activations