© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18003
    Prev
    Next
    INDEX
    Explanations

    phrases related to cost-sharing and cost-effectiveness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cost-effective strategies and funding

    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
     Hollow
    -0.70
    ADRA
    -0.70
    amber
    -0.70
    psc
    -0.69
    Ü
    -0.67
    vez
    -0.65
     Skull
    -0.65
    rouch
    -0.65
    eor
    -0.65
    oplan
    -0.64
    POSITIVE LOGITS
    benefit
    1.14
     incurred
    0.97
    efficiency
    0.85
    effic
    0.82
     upkeep
    0.81
     Quantity
    0.80
     overrun
    0.80
    effective
    0.79
    effect
    0.79
    efficient
    0.77
    Activations Density 0.165%

    No Known Activations