© 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. 10-RES-JB
    11. 21517
    Prev
    Next
    INDEX
    Explanations

    words related to recycling and waste management

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to environmental and economic resource management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Messages
    -0.65
    rief
    -0.64
     Detection
    -0.64
    odiac
    -0.63
    episode
    -0.63
     Topics
    -0.63
     playthrough
    -0.61
    idelines
    -0.61
     chronological
    -0.61
    Session
    -0.60
    POSITIVE LOGITS
     subsid
    1.46
     profits
    1.38
     cheaper
    1.37
     profit
    1.36
     revenues
    1.26
     profitable
    1.25
     subsidy
    1.24
     profitability
    1.23
     subsidized
    1.22
     privat
    1.22
    Activations Density 1.032%

    No Known Activations