© 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. 7-RES-JB
    11. 7474
    Prev
    Next
    INDEX
    Explanations

    phrases related to peer-to-peer interactions, financial transactions, and alternative economic models

    oai_token-act-pair · gpt-3.5-turbo

    topics and terms related to peer-to-peer economic systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ©ãĥ³
    -0.74
    Damage
    -0.70
    Destroy
    -0.68
    Winged
    -0.66
     Stevens
    -0.65
     Ashes
    -0.64
    Dust
    -0.63
    damage
    -0.63
    OIL
    -0.63
    ãĤĵ
    -0.62
    POSITIVE LOGITS
     decentralized
    0.85
     pioneered
    0.84
     cryptocurrencies
    0.81
     enabled
    0.80
    opoly
    0.79
     subscriptions
    0.78
     mediation
    0.78
     cryptocurrency
    0.77
     legalized
    0.76
     schemes
    0.76
    Activations Density 1.197%

    No Known Activations