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. 10-RES-JB
    6. 11863
    Prev
    Next
    INDEX
    Explanations

    titles or positions of authority in organizations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the roles of presidents and CEOs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asions
    -0.78
    antics
    -0.74
    utic
    -0.73
    zees
    -0.73
    arettes
    -0.70
    é¾įå
    -0.70
    unks
    -0.68
    xual
    -0.68
    ilet
    -0.67
    Pick
    -0.67
    POSITIVE LOGITS
     CEO
    1.72
     chief
    1.48
    CEO
    1.47
     chairman
    1.40
     founder
    1.38
     director
    1.25
     propriet
    1.25
     chancellor
    1.20
     publisher
    1.20
     administrator
    1.20
    Activations Density 0.051%

    No Known Activations