© 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. 6-RES-JB
    11. 13753
    Prev
    Next
    INDEX
    Explanations

    names of places or entities with a specific pattern, where the activation is particularly high for names ending in 'aki', 'ow', 'ato', and 'inus'

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of places and people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     carbohyd
    -0.82
    jriwal
    -0.82
    etheless
    -0.75
    aepernick
    -0.74
    arcity
    -0.71
     millenn
    -0.67
     nationally
    -0.67
     conduc
    -0.66
    ailability
    -0.66
    sheet
    -0.65
    POSITIVE LOGITS
     Brothers
    1.01
     Canyon
    1.00
     County
    0.98
     Mountains
    0.98
     Farms
    0.97
     Valley
    0.97
     Islands
    0.97
    stown
    0.95
     Downs
    0.94
    je
    0.90
    Activations Density 0.434%

    No Known Activations