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. 21241
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning or related to the title or role of "Commissioner"

    oai_token-act-pair · gpt-3.5-turbo

    the title and references to various commissioners

    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
    stream
    -0.83
    nikov
    -0.70
    pressure
    -0.69
    bra
    -0.67
    enes
    -0.67
    heid
    -0.65
    crew
    -0.65
    arrass
    -0.63
    imm
    -0.61
    nesses
    -0.60
    POSITIVE LOGITS
     Commissioner
    1.00
     commissioner
    0.98
    Commission
    0.85
    obook
    0.79
     Commissioners
    0.79
     commissioners
    0.76
    IAL
    0.73
     Headquarters
    0.73
    osal
    0.66
     overseeing
    0.65
    Activations Density 0.020%

    No Known Activations