© 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. 2-RES-JB
    11. 17582
    Prev
    Next
    INDEX
    Explanations

    instances where there is uncertainty or lack of knowledge

    oai_token-act-pair · gpt-3.5-turbo

    the word "about" in various contexts

    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
     Peaks
    -0.69
     Writ
    -0.65
    ©¶æ¥µ
    -0.65
    gallery
    -0.64
    Lens
    -0.62
    oly
    -0.61
    HT
    -0.61
    ¯¯¯¯¯¯¯¯
    -0.60
    OGR
    -0.59
    rift
    -0.59
    POSITIVE LOGITS
     halfway
    0.86
     respecting
    0.66
     660
    0.65
     midway
    0.65
     260
    0.65
     how
    0.64
     250
    0.63
     protecting
    0.60
     270
    0.60
     125
    0.59
    Activations Density 0.153%

    No Known Activations