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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 22564
    Prev
    Next
    INDEX
    Explanations

    phrases related to funding and financial resources

    oai_token-act-pair · gpt-3.5-turbo

    terms related to government funding and financial allocations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĶģ
    -0.75
    alan
    -0.75
    ozyg
    -0.75
    icol
    -0.72
     sidx
    -0.71
    weet
    -0.69
    soType
    -0.68
    ta
    -0.68
    eat
    -0.67
    ogyn
    -0.67
    POSITIVE LOGITS
     infrastructure
    1.27
     programs
    1.17
     reconstruction
    1.17
     highways
    1.15
     rebuilding
    1.14
     roads
    1.10
     education
    1.07
     repairing
    1.07
     projects
    1.07
     schools
    1.04
    Activations Density 0.332%

    No Known Activations