© 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. 12613
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific geographical location named Dunedin

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Dun" and its variants within the text

    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
    OHN
    -0.74
    xual
    -0.72
    âĸĪâĸĪ
    -0.66
    INC
    -0.65
    >>>>>>>>
    -0.65
    NRS
    -0.65
     pains
    -0.64
    Magikarp
    -0.62
     Pyro
    -0.61
    76561
    -0.60
    POSITIVE LOGITS
    wich
    1.05
    edin
    1.02
    igan
    1.01
    querque
    1.01
    lap
    0.97
    ning
    0.93
    geon
    0.93
    leys
    0.93
    ogh
    0.90
    geons
    0.90
    Activations Density 0.026%

    No Known Activations