© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 21434
    Prev
    Next
    INDEX
    Explanations

    negations or exceptions

    oai_token-act-pair · gpt-3.5-turbo

    negation phrases emphasizing what is not the case

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Companies
    -0.74
    éĥ
    -0.70
    stakes
    -0.69
    eur
    -0.69
     Inventory
    -0.67
    WAY
    -0.66
    SER
    -0.65
    riber
    -0.65
    itor
    -0.65
    ership
    -0.64
    POSITIVE LOGITS
     necessarily
    1.37
    icably
    1.37
    icable
    1.19
    epad
    1.19
     exactly
    0.99
    withstanding
    0.96
     yet
    0.96
    orious
    0.91
     bothering
    0.88
    necess
    0.88
    Activations Density 0.297%

    No Known Activations