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. 8272
    Prev
    Next
    INDEX
    Explanations

    words related to power, control, and authority

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dominance and control in various contexts

    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
    ead
    -0.77
    enegger
    -0.74
    pt
    -0.69
    abet
    -0.67
    idan
    -0.67
    endment
    -0.67
    ange
    -0.66
    Afee
    -0.64
    den
    -0.64
    gnu
    -0.63
    POSITIVE LOGITS
     mentality
    0.71
     hierarch
    0.71
     bidder
    0.70
     mindset
    0.69
     headlines
    0.68
     precedence
    0.67
     dominate
    0.67
     charge
    0.66
     dominated
    0.65
    mind
    0.64
    Activations Density 0.078%

    No Known Activations