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. 17015
    Prev
    Next
    INDEX
    Explanations

    numerical references to punishment or sentencing durations in years

    oai_token-act-pair · gpt-3.5-turbo

    long prison sentences

    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
     VIDEOS
    -0.96
     Collider
    -0.89
    ople
    -0.78
    acly
    -0.71
    achus
    -0.66
    Spawn
    -0.65
    inite
    -0.65
    atech
    -0.65
    Mom
    -0.65
    edia
    -0.64
    POSITIVE LOGITS
     ago
    1.23
     apiece
    1.00
     probation
    0.92
     Ago
    0.87
     imprisonment
    0.84
    long
    0.78
     overdue
    0.74
     incarceration
    0.73
     olds
    0.72
     consecut
    0.72
    Activations Density 0.087%

    No Known Activations