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. 549
    Prev
    Next
    INDEX
    Explanations

    phrases related to employment struggles in Germany

    oai_token-act-pair · gpt-3.5-turbo

    articles and pronouns indicating individuals or entities

    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
     Cheong
    -0.71
    ruary
    -0.69
    Beat
    -0.62
    Reviewed
    -0.62
    escription
    -0.59
     Jackie
    -0.58
     Swordsman
    -0.58
     Admir
    -0.58
     Goose
    -0.57
     ASIC
    -0.57
    POSITIVE LOGITS
    士
    0.80
    pta
    0.77
    omal
    0.75
    imaru
    0.70
    illance
    0.70
    chal
    0.70
    aman
    0.69
    etsk
    0.69
    agus
    0.69
    acus
    0.69
    Activations Density 0.420%

    No Known Activations