© 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. 3-RES-JB
    11. 1807
    Prev
    Next
    INDEX
    Explanations

    mentions of specific news organizations like HuffPost and Vox

    oai_token-act-pair · gpt-3.5-turbo

    mentions of media outlets or news organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.76
    ces
    -0.68
    ========
    -0.67
    gio
    -0.63
    arters
    -0.61
    cream
    -0.61
    OTS
    -0.60
    othy
    -0.60
    lass
    -0.59
    oneliness
    -0.59
    POSITIVE LOGITS
    edIn
    0.93
    shire
    0.90
     HuffPost
    0.87
    odox
    0.74
    icity
    0.68
    aires
    0.68
    entimes
    0.67
     affiliate
    0.66
    igen
    0.66
    aukee
    0.65
    Activations Density 0.005%

    No Known Activations