© 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. 10-RES-JB
    11. 11184
    Prev
    Next
    INDEX
    Explanations

    phrases related to something being beyond a certain point or limit

    oai_token-act-pair · gpt-3.5-turbo

    expressions that indicate limits being surpassed or situations going beyond normal boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    si
    -0.75
    nian
    -0.69
    cu
    -0.68
    asses
    -0.68
    male
    -0.65
    vic
    -0.62
    ICAN
    -0.62
    sb
    -0.61
    ANS
    -0.61
    female
    -0.61
    POSITIVE LOGITS
     comprehension
    0.90
     mere
    0.89
     imagining
    0.89
     Borders
    0.86
     redemption
    0.82
     doubt
    0.81
     bounds
    0.81
    iche
    0.79
     repair
    0.77
     recognition
    0.76
    Activations Density 0.041%

    No Known Activations