© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 22753
    Prev
    Next
    INDEX
    Explanations

    mentions of large companies or corporations

    oai_token-act-pair · gpt-3.5-turbo

    references to large companies or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jured
    -0.83
    zbollah
    -0.76
    iggins
    -0.76
    yrinth
    -0.75
    veyard
    -0.71
    tein
    -0.71
    icter
    -0.70
    eq
    -0.70
    agan
    -0.69
    qi
    -0.69
    POSITIVE LOGITS
     titan
    1.08
     giants
    0.90
     corporation
    0.90
     corporations
    0.88
     multinational
    0.83
     conglomerate
    0.79
     shareholder
    0.79
     advertis
    0.79
     retailer
    0.76
     CEO
    0.76
    Activations Density 0.019%

    No Known Activations