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. 17929
    Prev
    Next
    INDEX
    Explanations

    phrases related to convergence or coming together

    oai_token-act-pair · gpt-3.5-turbo

    instances of gathering or assembly

    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
    wx
    -0.87
    ATER
    -0.86
    gebra
    -0.81
    maxwell
    -0.80
    antom
    -0.70
    enza
    -0.67
    Grey
    -0.66
    yrus
    -0.66
    irit
    -0.65
    Desk
    -0.65
    POSITIVE LOGITS
     manag
    0.66
     independent
    0.65
    quartered
    0.62
     independ
    0.62
     Universities
    0.62
    len
    0.62
     MPG
    0.61
     Cosponsors
    0.61
     museums
    0.59
    uez
    0.58
    Activations Density 0.000%

    No Known Activations