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. 22140
    Prev
    Next
    INDEX
    Explanations

    references to criminal investigations and legal proceedings related to assaults and abuse

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sexual misconduct and the legal system surrounding it

    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
    WATCH
    -0.76
    å§«
    -0.73
    IENT
    -0.71
    RECT
    -0.71
    IRD
    -0.71
    é¾įåĸļ士
    -0.70
    Js
    -0.69
    vale
    -0.69
    å°Ĩ
    -0.67
    RANT
    -0.66
    POSITIVE LOGITS
    dq
    0.71
     backlog
    0.70
     Cambodia
    0.67
     hotline
    0.65
    amph
    0.64
     Faul
    0.63
     PTSD
    0.61
     allowance
    0.61
    ascus
    0.61
     blacklist
    0.60
    Activations Density 0.358%

    No Known Activations