Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 16679
    Prev
    Next
    INDEX
    Explanations

    names related to political or social figures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "idi" and its variations, suggesting a focus on the concept of identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebin
    -0.72
     guiActiveUnfocused
    -0.69
     inaction
    -0.66
    DOC
    -0.65
    cffffcc
    -0.64
    talk
    -0.63
    rooms
    -0.63
    ^^^^
    -0.61
    north
    -0.61
    deck
    -0.61
    POSITIVE LOGITS
    idis
    1.11
    opsis
    1.03
    hedral
    0.88
     Beir
    0.88
    Äĩ
    0.87
    emy
    0.85
    idi
    0.84
    roid
    0.80
    cipl
    0.80
    etics
    0.79
    Activations Density 0.010%

    No Known Activations