© 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. 2782
    Prev
    Next
    INDEX
    Explanations

    references to specific brand names, specifically "Monsanto" and "Bayer."

    oai_token-act-pair · gpt-3.5-turbo

    references to the brand names of agricultural companies and their associated products

    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
    eworks
    -0.84
    mate
    -0.84
    shaw
    -0.76
    sets
    -0.75
    book
    -0.74
    ded
    -0.74
    drivers
    -0.72
    ulative
    -0.72
    points
    -0.70
    ding
    -0.70
    POSITIVE LOGITS
    anto
    1.09
     ASA
    0.86
    terday
    0.79
     breathe
    0.76
     Pharmaceutical
    0.74
    xon
    0.73
    omach
    0.70
     indust
    0.69
     Pharma
    0.67
    opa
    0.66
    Activations Density 0.018%

    No Known Activations