© 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. 9-RES-JB
    11. 7321
    Prev
    Next
    INDEX
    Explanations

    places or venues that are open to the public

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or spaces that are open to the public

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ̶
    -0.78
    wark
    -0.74
    terness
    -0.69
     à¤
    -0.68
    nesia
    -0.68
    hemat
    -0.67
    olate
    -0.66
    ruary
    -0.65
     captcha
    -0.65
    aryn
    -0.65
    POSITIVE LOGITS
     tourists
    1.35
     visitors
    1.32
     guests
    1.29
     occupants
    1.24
     pilgrims
    1.12
     hikers
    1.10
     occupancy
    1.05
     tenants
    1.04
     pedestrians
    1.04
     spectators
    1.03
    Activations Density 0.950%

    No Known Activations