© 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. 11-RES-JB
    11. 118
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a specific focus or attention on certain topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases or clauses that reference explicit conditions or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gladly
    -0.77
    ĺħ
    -0.71
     likewise
    -0.70
     Nope
    -0.69
     regardless
    -0.68
     irrespective
    -0.68
    yeah
    -0.67
    successfully
    -0.66
     everywhere
    -0.66
    regate
    -0.66
    POSITIVE LOGITS
     regards
    1.07
     cases
    1.04
     regard
    0.99
     relation
    0.94
     areas
    0.90
     conjunction
    0.88
     instances
    0.87
     situations
    0.85
     light
    0.85
     contexts
    0.83
    Activations Density 0.178%

    No Known Activations