© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 8798
    Prev
    Next
    INDEX
    Explanations

    URLs from the Google Drive domain

    oai_token-act-pair · gpt-3.5-turbo

    URLs that include "google.com" or "youtube.com"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.82
     Balt
    -0.74
    ĺħ
    -0.69
     steroids
    -0.66
     almonds
    -0.64
    Berry
    -0.62
     burgl
    -0.62
    ById
    -0.61
     governors
    -0.60
     snowball
    -0.60
    POSITIVE LOGITS
    lisher
    1.01
    psons
    0.97
    pleted
    0.96
    ptroller
    0.94
    ittee
    0.94
    lishing
    0.93
    biz
    0.90
    fortable
    0.86
    ensen
    0.84
    nl
    0.84
    Activations Density 0.032%

    No Known Activations