Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 20433
    Prev
    Next
    INDEX
    Explanations

    words related to giving commands or instructions

    oai_token-act-pair · gpt-3.5-turbo

    instances of authoritative commands or orders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.83
    figure
    -0.83
    nown
    -0.81
     sidx
    -0.81
    vir
    -0.80
    yip
    -0.79
    common
    -0.78
    uded
    -0.77
    alth
    -0.77
    attery
    -0.77
    POSITIVE LOGITS
     evacuation
    0.89
     subordinates
    0.88
     demolition
    0.88
     extermin
    0.82
     execution
    0.82
     executions
    0.82
     removal
    0.82
     deported
    0.80
     extermination
    0.80
     attention
    0.80
    Activations Density 0.081%

    No Known Activations