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. 1-RES-JB
    6. 12258
    Prev
    Next
    INDEX
    Explanations

    references to designers in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of designers in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pradesh
    -0.75
     Locked
    -0.69
    Hig
    -0.66
     ILCS
    -0.66
    iland
    -0.66
    ibaba
    -0.65
    zees
    -0.65
     Territories
    -0.64
    ili
    -0.63
    apters
    -0.62
    POSITIVE LOGITS
     designer
    1.33
    urally
    0.99
     designers
    0.96
     Designer
    0.93
    yout
    0.85
     planner
    0.82
     designing
    0.82
     redesign
    0.81
     cout
    0.81
     design
    0.81
    Activations Density 0.008%

    No Known Activations