© 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. 10662
    Prev
    Next
    INDEX
    Explanations

    phrases related to commercial activities or products

    oai_token-act-pair · gpt-3.5-turbo

    terms related to commercial products and notable figures involved in technology and business

    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
     Antar
    -0.74
    gery
    -0.71
    allah
    -0.70
    sett
    -0.68
    ber
    -0.65
    iger
    -0.64
    gra
    -0.64
    undo
    -0.63
    gie
    -0.63
     Palest
    -0.63
    POSITIVE LOGITS
    ickr
    0.89
    LEASE
    0.85
    sylvania
    0.83
    otle
    0.80
    UTERS
    0.79
    Series
    0.78
    çĶ°
    0.78
     Flavoring
    0.78
    ensable
    0.77
    ONSORED
    0.74
    Activations Density 0.033%

    No Known Activations