© 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. 528
    Prev
    Next
    INDEX
    Explanations

    phrases or lists of items introduced by a colon

    oai_token-act-pair · gpt-3.5-turbo

    various categories and classifications related to specific subjects

    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
    wan
    -0.72
    azaki
    -0.62
    ahime
    -0.62
    yan
    -0.59
     Copyright
    -0.58
    hao
    -0.58
     fuck
    -0.58
     Accessed
    -0.58
    orses
    -0.58
    ammed
    -0.58
    POSITIVE LOGITS
     namely
    1.00
    hemat
    0.77
     Firstly
    0.76
     notably
    0.75
    aspberry
    0.73
     awa
    0.71
     Including
    0.71
     viz
    0.71
     includ
    0.67
    including
    0.65
    Activations Density 0.558%

    No Known Activations