© 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. 8-RES-JB
    11. 6950
    Prev
    Next
    INDEX
    Explanations

    locations and events related to the city of Aleppo in Syria

    oai_token-act-pair · gpt-3.5-turbo

    references to Aleppo and related military actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ©
    -0.84
    pointers
    -0.76
    ificate
    -0.76
    uador
    -0.73
    ublic
    -0.72
    morph
    -0.70
    ritten
    -0.69
    ulhu
    -0.69
    ificial
    -0.68
    nis
    -0.68
    POSITIVE LOGITS
     Province
    0.90
     countryside
    0.89
    ascus
    0.75
     Heights
    0.75
     municipality
    0.74
     Bust
    0.73
     Aleppo
    0.73
     rall
    0.72
     Municip
    0.71
     neighbourhoods
    0.70
    Activations Density 0.049%

    No Known Activations