© 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. 7-RES-JB
    11. 12420
    Prev
    Next
    INDEX
    Explanations

    locations or places, particularly national parks and communities

    oai_token-act-pair · gpt-3.5-turbo

    references to locations associated with national parks, communities, and other public institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.91
    pread
    -0.67
     ante
    -0.65
     tread
    -0.64
    erity
    -0.62
    ^^^^
    -0.62
    erella
    -0.61
    hematically
    -0.60
    Pg
    -0.60
     horny
    -0.59
    POSITIVE LOGITS
     Complex
    1.14
     Cooperative
    1.11
     Facility
    1.03
     Resort
    1.01
     School
    0.96
     Station
    0.95
     Estate
    0.94
     Loans
    0.92
     Clinic
    0.92
     Center
    0.92
    Activations Density 0.229%

    No Known Activations