© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 6910
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for references to a specific location named Tah

    oai_token-act-pair · gpt-3.5-turbo

    references to "Tahrir Square" and its associated elements

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

    No Comments

    Negative Logits
    mble
    -0.74
    ISTER
    -0.71
     fixation
    -0.68
    ancial
    -0.67
    ablishment
    -0.65
     cov
    -0.65
    heid
    -0.61
    VERSION
    -0.61
     Purg
    -0.59
     quirks
    -0.59
    POSITIVE LOGITS
    oya
    1.02
    rir
    0.98
     Tah
    0.97
    anus
    0.91
    essa
    0.90
    iti
    0.89
    una
    0.88
    ania
    0.85
    ibi
    0.85
    iri
    0.85
    Activations Density 0.007%

    No Known Activations