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. 24447
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and courtroom activities

    oai_token-act-pair · gpt-3.5-turbo

    references to juries in legal contexts

    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
     Franch
    -0.73
    irst
    -0.68
    zl
    -0.66
     Occupations
    -0.65
     Trip
    -0.64
    dayName
    -0.62
    erenn
    -0.62
     Patient
    -0.62
    oms
    -0.61
    ospital
    -0.61
    POSITIVE LOGITS
    glass
    0.84
     jury
    0.84
    proof
    0.78
     verdict
    0.77
     jurors
    0.77
    rooms
    0.74
    room
    0.74
    Panel
    0.71
    ĵĺ
    0.70
    member
    0.69
    Activations Density 0.014%

    No Known Activations