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. 4-RES-JB
    6. 5527
    Prev
    Next
    INDEX
    Explanations

    words related to place names, specifically those ending in 'iya' or 'iyah'

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographical or cultural identifiers in a region

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

    No Comments

    Negative Logits
    shire
    -0.83
    auld
    -0.81
    acles
    -0.80
    rance
    -0.79
    bone
    -0.78
    egg
    -0.77
    agon
    -0.77
    ees
    -0.75
    cot
    -0.75
    ergy
    -0.74
    POSITIVE LOGITS
    BILITY
    1.07
    icago
    0.81
    BIL
    0.81
    veland
    0.73
    ignty
    0.72
    ÅĤ
    0.72
    BILITIES
    0.70
    ³³³³³³³³³³³³³³³³
    0.70
     yr
    0.70
    Äĩ
    0.70
    Activations Density 0.030%

    No Known Activations