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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 5282
    Prev
    Next
    INDEX
    Explanations

    We couldn't find a clear pattern in the activations provided for Neuron 4

    oai_token-act-pair · gpt-3.5-turbo

    instances of URLs, particularly those related to social media platforms like Twitter and YouTube

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grounding
    -0.74
    ĪĴ
    -0.68
     tampering
    -0.67
     galvan
    -0.61
     orally
    -0.60
     distilled
    -0.60
     vibrations
    -0.60
    -+-+
    -0.58
    Ļ½
    -0.58
    AFTA
    -0.58
    POSITIVE LOGITS
    com
    1.18
    facebook
    1.02
    php
    0.97
    apple
    0.96
    github
    0.90
    html
    0.87
    gnu
    0.85
    nl
    0.85
    twitter
    0.84
    tv
    0.82
    Activations Density 0.048%

    No Known Activations