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. 2009
    Prev
    Next
    INDEX
    Explanations

    terms related to peripheral items or devices, such as "peripheral vision" and "peripheral immune systems."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to peripheral elements and medical contexts, particularly involving vision and firearms

    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
    ij士
    -0.88
    ancouver
    -0.81
    inations
    -0.74
    ancy
    -0.73
    mie
    -0.72
    ADRA
    -0.72
    ainers
    -0.72
    orie
    -0.72
    borgh
    -0.71
    ansas
    -0.71
    POSITIVE LOGITS
    ãĥĥãĤ¯
    0.82
    NetMessage
    0.81
    issance
    0.73
    fold
    0.69
    manship
    0.67
    merce
    0.66
     Mehran
    0.66
     nib
    0.64
    ÅĤ
    0.64
    Downloadha
    0.64
    Activations Density 0.050%

    No Known Activations