© 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. 1-RES-JB
    11. 3688
    Prev
    Next
    INDEX
    Explanations

    keywords related to encryption, data security, and internet technologies

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific key or keyword

    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
    ional
    -0.77
    actionDate
    -0.69
    stru
    -0.66
    saving
    -0.65
    conv
    -0.63
    acity
    -0.61
    naire
    -0.60
    tested
    -0.60
    ione
    -0.59
    battle
    -0.59
    POSITIVE LOGITS
    KE
    1.45
    YS
    1.05
    LEY
    1.00
    VO
    0.99
    OPLE
    0.91
    IRO
    0.89
    ETS
    0.87
    FU
    0.85
    AK
    0.85
    LL
    0.84
    Activations Density 0.006%

    No Known Activations