© 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. 17261
    Prev
    Next
    INDEX
    Explanations

    instances of the word "mac" in the text

    oai_token-act-pair · gpt-3.5-turbo

    descriptors indicating extreme negative outcomes

    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
    phia
    -0.76
     Defeat
    -0.75
    urers
    -0.71
     corro
    -0.69
    phy
    -0.67
    onen
    -0.66
    mons
    -0.66
     Antiqu
    -0.65
    uscript
    -0.64
     deceive
    -0.64
    POSITIVE LOGITS
    é»Ĵ
    0.75
    rawdownloadcloneembedreportprint
    0.68
     baths
    0.66
     BASE
    0.65
    ãĥĺãĥ©
    0.64
     pairs
    0.64
     GDDR
    0.63
    inous
    0.62
    /**
    0.61
    OTAL
    0.60
    Activations Density 0.000%

    No Known Activations