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. 114
    Prev
    Next
    INDEX
    Explanations

    phrases related to law enforcement officials and their titles

    oai_token-act-pair · gpt-3.5-turbo

    titles and roles related to law enforcement and education administration

    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
    PsyNetMessage
    -0.78
    76561
    -0.75
     CET
    -0.73
    ted
    -0.70
    plets
    -0.67
    apore
    -0.66
    carbon
    -0.65
    bra
    -0.64
    British
    -0.63
    ubuntu
    -0.63
    POSITIVE LOGITS
     commissioner
    0.89
     superintendent
    0.87
     Superintendent
    0.82
     Lori
    0.76
     Marty
    0.74
     Stacy
    0.74
     Commissioner
    0.74
     Shawn
    0.72
     examiner
    0.70
     district
    0.70
    Activations Density 0.110%

    No Known Activations