© 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. 1-RES-JB
    11. 6660
    Prev
    Next
    INDEX
    Explanations

    content related to online advertising platforms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "taboola" and related web content structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etimes
    -0.78
    eg
    -0.77
    itar
    -0.76
    ions
    -0.74
    coming
    -0.74
    icles
    -0.72
    iate
    -0.70
    ities
    -0.70
    ieth
    -0.68
    itarian
    -0.67
    POSITIVE LOGITS
    taboola
    1.59
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.89
    ````
    0.82
    #$#$
    0.78
    renheit
    0.78
    ridor
    0.76
    CLASSIFIED
    0.76
     certs
    0.72
    BuyableInstoreAndOnline
    0.71
    olla
    0.71
    Activations Density 0.012%

    No Known Activations