© 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. 4-RES-JB
    11. 7048
    Prev
    Next
    INDEX
    Explanations

    negative critiques or shortcomings in sports-related contexts

    oai_token-act-pair · gpt-3.5-turbo

    the indefinite article "a" in various contexts

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

    No Comments

    Negative Logits
     Ideas
    -0.87
    encies
    -0.82
    cair
    -0.81
    SOURCE
    -0.77
    coins
    -0.73
     Actions
    -0.73
    Shares
    -0.71
     ®
    -0.71
     Mormons
    -0.71
    Images
    -0.70
    POSITIVE LOGITS
    venge
    1.09
     whopping
    1.08
     plethora
    1.06
     flurry
    1.02
     bunch
    1.00
     slew
    1.00
     terrific
    0.99
     blister
    0.99
     timely
    0.97
     sizeable
    0.96
    Activations Density 0.472%

    No Known Activations