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. 5-RES-JB
    6. 7525
    Prev
    Next
    INDEX
    Explanations

    mentions of personal or private aspects of individuals' lives, such as home, behavior, reactions, living conditions, work, etc

    oai_token-act-pair · gpt-3.5-turbo

    references to home and personal experiences

    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
     Samar
    -0.68
    atton
    -0.66
     Guan
    -0.66
    ©¶æ
    -0.65
    etheless
    -0.63
    asus
    -0.62
     Horizon
    -0.61
     myself
    -0.61
     Tycoon
    -0.60
     Beckham
    -0.60
    POSITIVE LOGITS
     selves
    1.42
     counterparts
    1.23
     brethren
    0.85
    respective
    0.75
     holdings
    0.75
     careers
    0.74
     overl
    0.71
     lives
    0.71
     arsenal
    0.70
     neighbours
    0.70
    Activations Density 0.385%

    No Known Activations