© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20013
    Prev
    Next
    INDEX
    Explanations

    descriptions or features related to square or squared items

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "square" in various contexts

    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
    ARP
    -0.75
     Gloss
    -0.68
    esta
    -0.66
     Prol
    -0.66
    agi
    -0.65
    igers
    -0.63
     Helpful
    -0.62
    angered
    -0.61
    oan
    -0.61
     Fathers
    -0.60
    POSITIVE LOGITS
     square
    1.19
     Enix
    1.05
     squares
    1.04
    square
    0.97
    Square
    0.89
     squared
    0.87
     Square
    0.80
     spacing
    0.78
    sq
    0.76
     sq
    0.76
    Activations Density 0.009%

    No Known Activations