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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 10-RES-JB
    6. 9796
    Prev
    Next
    INDEX
    Explanations

    people along with their professions or roles they play

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate possession of experience or qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wake
    -0.72
    tenance
    -0.71
     blocker
    -0.62
    initions
    -0.61
    BF
    -0.60
    pool
    -0.59
    pez
    -0.59
    rection
    -0.58
    try
    -0.58
    are
    -0.58
    POSITIVE LOGITS
     whom
    1.38
    stood
    1.11
     ties
    1.09
     expertise
    1.08
     impecc
    1.06
     delusions
    0.99
     aspirations
    0.97
     clout
    0.93
     credentials
    0.93
     ambitions
    0.91
    Activations Density 0.140%

    No Known Activations