© 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. 13194
    Prev
    Next
    INDEX
    Explanations

    the word "Ar" followed by a number, potentially related to specific entities or actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Arne" across various contexts

    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
    ĸļ
    -0.81
    姫
    -0.78
    ãģ®éŃĶ
    -0.72
     Pioneer
    -0.68
    aneers
    -0.67
    stakes
    -0.66
    eners
    -0.66
     Rasmussen
    -0.65
    ¬¼
    -0.63
     Vide
    -0.63
    POSITIVE LOGITS
    idon
    0.97
    izoph
    0.92
    thritis
    0.92
    ithmetic
    0.92
    rival
    0.89
    rived
    0.89
    ansas
    0.87
    amaz
    0.86
    beit
    0.85
    asu
    0.84
    Activations Density 0.005%

    No Known Activations