© 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. 20021
    Prev
    Next
    INDEX
    Explanations

    terms related to sources of various things like information, income, employment, and discord

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to sources of revenue or support

    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
    wagen
    -0.92
    Ń·
    -0.81
    arat
    -0.80
     WATCHED
    -0.75
    048
    -0.69
    ACY
    -0.68
    lake
    -0.68
    taker
    -0.68
    agate
    -0.66
    boxing
    -0.66
    POSITIVE LOGITS
     inspiration
    1.19
     sust
    1.03
     income
    0.96
     revenue
    0.94
     wealth
    0.90
     employment
    0.89
     funds
    0.85
     manpower
    0.85
     funding
    0.85
     assistance
    0.83
    Activations Density 0.070%

    No Known Activations