© 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. 3-RES-JB
    11. 526
    Prev
    Next
    INDEX
    Explanations

    references to subway stations or subway-related activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of subway systems or stations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ei
    -0.71
    ificial
    -0.69
    CLASSIFIED
    -0.67
    yer
    -0.65
    iyah
    -0.64
    laus
    -0.64
    wine
    -0.64
    letico
    -0.63
    EMP
    -0.63
    é»Ĵ
    -0.63
    POSITIVE LOGITS
     subway
    1.13
     Subway
    1.01
     commute
    0.82
     station
    0.81
     tunnels
    0.81
     entrances
    0.79
     stations
    0.79
     commuting
    0.78
     plaza
    0.77
     commuter
    0.77
    Activations Density 0.010%

    No Known Activations