© 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. 4282
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical locations with a focus on Baltic states, especially Latvia

    oai_token-act-pair · gpt-3.5-turbo

    references to "Latina" or "Latino" themes or entities

    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
    éĹĺ
    -0.78
    OHN
    -0.72
    ħĭ
    -0.71
    CRIP
    -0.71
    EMENT
    -0.68
    ERC
    -0.67
    MODE
    -0.67
    ãģ®éŃĶ
    -0.67
    vironment
    -0.66
    FactoryReloaded
    -0.66
    POSITIVE LOGITS
    itude
    1.27
    itud
    1.25
    itudinal
    1.21
    imes
    1.05
    itudes
    1.04
    akia
    1.02
    robe
    0.96
    imore
    0.90
    ania
    0.89
    ency
    0.86
    Activations Density 0.034%

    No Known Activations