© 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. 2-RES-JB
    11. 13875
    Prev
    Next
    INDEX
    Explanations

    phrases related to editing or modified content

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "edited"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lay
    -0.80
    ingham
    -0.80
    vor
    -0.72
    clerosis
    -0.70
    CVE
    -0.70
    lust
    -0.67
    gaard
    -0.66
    adra
    -0.65
    fell
    -0.65
    stone
    -0.65
    POSITIVE LOGITS
    ieval
    1.00
    escription
    1.00
     subur
    0.96
    uled
    0.95
     pione
    0.86
     millenn
    0.80
    ÃĥÃĤ
    0.79
     practition
    0.77
    monton
    0.76
    DeliveryDate
    0.75
    Activations Density 0.063%

    No Known Activations