© 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. 16484
    Prev
    Next
    INDEX
    Explanations

    Spanish verbs ending in 'ar'

    oai_token-act-pair · gpt-3.5-turbo

    the word "que" and its variations in the context of conditional or causal statements

    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
    ERAL
    -0.92
    ãĤ¼ãĤ¦ãĤ¹
    -0.82
    ãĥĩ
    -0.77
    ãĥŁ
    -0.75
    anmar
    -0.74
    ohyd
    -0.74
    opathic
    -0.73
    cipline
    -0.73
    uania
    -0.71
    opathy
    -0.69
    POSITIVE LOGITS
     Que
    1.01
     que
    0.88
    ued
    0.84
    uing
    0.83
    erness
    0.82
    iu
    0.82
    que
    0.77
     Wilde
    0.74
    ep
    0.74
    bec
    0.74
    Activations Density 0.005%

    No Known Activations