© 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. 4-RES-JB
    11. 9487
    Prev
    Next
    INDEX
    Explanations

    mentions of keywords or acronyms related to internet technologies (e.g., "Internet Key Exchange")

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific keywords related to a particular concept or entity

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

    No Comments

    Negative Logits
    naire
    -0.84
    ional
    -0.79
    actionDate
    -0.78
    inally
    -0.75
    ione
    -0.71
    orer
    -0.67
    agna
    -0.66
    inant
    -0.66
     thous
    -0.65
    atically
    -0.65
    POSITIVE LOGITS
    KE
    1.12
    YS
    1.00
    LEY
    0.99
    VO
    0.89
    LAND
    0.84
    IRO
    0.83
    VERS
    0.81
    ACH
    0.81
    ITH
    0.80
    ECH
    0.78
    Activations Density 0.005%

    No Known Activations