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. 1-RES-JB
    6. 1174
    Prev
    Next
    INDEX
    Explanations

    words related to strict and rigid situations or structures

    oai_token-act-pair · gpt-3.5-turbo

    references to economic or ideological constraints

    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
    ULE
    -0.76
    ETF
    -0.74
     WARN
    -0.74
    ERAL
    -0.71
    Interstitial
    -0.70
    ICA
    -0.68
     Werewolf
    -0.67
    IFIC
    -0.66
    MAT
    -0.65
    MT
    -0.65
    POSITIVE LOGITS
     stra
    1.41
     Stra
    1.00
    pping
    0.90
    eties
    0.88
     Strait
    0.87
    pper
    0.86
    fing
    0.85
    cipled
    0.85
     tiss
    0.83
    obar
    0.81
    Activations Density 0.004%

    No Known Activations