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. 1428
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to equality, equivalence, or comparison

    oai_token-act-pair · gpt-3.5-turbo

    terms related to equality or equivalence

    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
    doms
    -0.86
    Assembly
    -0.80
     Skydragon
    -0.77
    ARD
    -0.73
    berries
    -0.73
     Soda
    -0.73
    ARDS
    -0.72
    HEAD
    -0.71
     Decay
    -0.68
    dom
    -0.67
    POSITIVE LOGITS
    ivil
    1.05
     equ
    1.03
    ilateral
    1.03
    ivalent
    0.99
    ifax
    0.96
    itably
    0.95
    ilib
    0.91
    als
    0.86
    ilater
    0.84
    agnetic
    0.82
    Activations Density 0.007%

    No Known Activations