© 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. 9-RES-JB
    11. 8876
    Prev
    Next
    INDEX
    Explanations

    verbs related to receiving or being bombarded with information

    oai_token-act-pair · gpt-3.5-turbo

    terms related to being overwhelmed or inundated

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istani
    -0.70
    quickShipAvailable
    -0.67
    tein
    -0.64
     partName
    -0.60
     Distance
    -0.60
    IFF
    -0.60
    edom
    -0.60
     vantage
    -0.60
    Balt
    -0.58
    nl
    -0.58
    POSITIVE LOGITS
     with
    1.18
     WITH
    0.98
    with
    0.96
     With
    0.96
     withd
    0.88
    With
    0.88
     coffers
    0.83
     inbox
    0.79
    icative
    0.72
     cortex
    0.62
    Activations Density 0.249%

    No Known Activations