Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 11532
    Prev
    Next
    INDEX
    Explanations

    locations and names of countries and individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific geographical locations, particularly Kuwait

    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
    BOOK
    -0.76
    MENTS
    -0.71
    ringe
    -0.67
    backer
    -0.64
    ãģ¦
    -0.64
    MENT
    -0.63
    beit
    -0.63
     energies
    -0.63
    yards
    -0.61
    berries
    -0.60
    POSITIVE LOGITS
    amiya
    0.84
    igon
    0.82
    iya
    0.80
    waukee
    0.80
    ipedia
    0.80
    iyah
    0.80
    oi
    0.80
    iang
    0.80
    iak
    0.79
    iy
    0.78
    Activations Density 0.014%

    No Known Activations