© 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. 3651
    Prev
    Next
    INDEX
    Explanations

    URLs and technical tags like iframes in a document

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "embed" and its variations

    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
    ãĥĥãĥĪ
    -0.92
    BuyableInstoreAndOnline
    -0.83
    »Ĵ
    -0.81
    代
    -0.80
    姫
    -0.76
    wagen
    -0.72
     è£ı
    -0.72
    Downloadha
    -0.72
     Fenrir
    -0.71
    ãĥīãĥ©
    -0.68
    POSITIVE LOGITS
    arrass
    1.16
    edded
    1.10
     Emb
    0.94
    ed
    0.91
    odied
    0.91
    emb
    0.89
    assies
    0.89
    embed
    0.88
    argo
    0.87
    edd
    0.86
    Activations Density 0.014%

    No Known Activations