© 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. 14232
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "berries."

    oai_token-act-pair · gpt-3.5-turbo

    plural nouns that refer to various types of items or entities

    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
     artificial
    -0.69
    earable
    -0.68
     unintention
    -0.65
     ana
    -0.65
    Reviewer
    -0.65
     abrupt
    -0.64
     intermittent
    -0.64
     tow
    -0.64
     superficial
    -0.63
     annexation
    -0.63
    POSITIVE LOGITS
    ries
    1.40
    eries
    0.96
    hops
    0.91
    mith
    0.88
    gaard
    0.86
    hop
    0.85
    pei
    0.84
    orio
    0.84
    lander
    0.82
    yt
    0.82
    Activations Density 0.007%

    No Known Activations