© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 22682
    Prev
    Next
    INDEX
    Explanations

    different types of crops and aspects related to agriculture

    oai_token-act-pair · gpt-3.5-turbo

    themes related to exploitation and economic disparity

    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
     Investigator
    -0.76
     Advocate
    -0.76
    nesday
    -0.70
     Observer
    -0.69
     Administrator
    -0.68
     Exam
    -0.67
     Operator
    -0.65
     Anon
    -0.64
     Avenger
    -0.64
     Commander
    -0.63
    POSITIVE LOGITS
     plantations
    0.99
     factories
    0.99
    boats
    0.98
    houses
    0.92
     crops
    0.92
     structures
    0.91
     networks
    0.90
    flies
    0.89
     gardens
    0.88
     farms
    0.88
    Activations Density 0.475%

    No Known Activations