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. 14530
    Prev
    Next
    INDEX
    Explanations

    factors, influencers, and topics related to various issues or concerns

    oai_token-act-pair · gpt-3.5-turbo

    significant nouns and phrases related to various social, political, and economic issues

    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
     IPM
    -0.73
    gger
    -0.68
     MMR
    -0.67
    utenberg
    -0.66
    iasis
    -0.65
    lua
    -0.64
     Shack
    -0.63
     Missile
    -0.63
     Sandwich
    -0.62
     Charity
    -0.61
    POSITIVE LOGITS
     besides
    1.06
    worldly
    0.92
     alike
    0.83
     than
    0.76
     describ
    0.74
     affili
    0.71
     factors
    0.70
     forms
    0.69
    illary
    0.68
     influences
    0.67
    Activations Density 0.308%

    No Known Activations