© 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. 8-RES-JB
    11. 20442
    Prev
    Next
    INDEX
    Explanations

    technical terms related to technology and digital marketing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technology and digital marketing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    flies
    -1.11
    fold
    -0.86
    rod
    -0.86
    atom
    -0.83
     ç¥ŀ
    -0.81
    craft
    -0.80
    folk
    -0.80
    wall
    -0.80
    lie
    -0.80
    chester
    -0.77
    POSITIVE LOGITS
    PDATE
    1.07
    HER
    1.03
    Vs
    0.97
    BIL
    0.97
    FP
    0.96
    BA
    0.94
    UE
    0.93
    WD
    0.91
    TING
    0.91
    BL
    0.91
    Activations Density 0.102%

    No Known Activations