Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 5832
    Prev
    Next
    INDEX
    Explanations

    mentions of the city "Raqqa" in the context of military operations and political activities

    oai_token-act-pair · gpt-3.5-turbo

    references to the location Raqqa and associated individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ASUS
    -0.74
     Jace
    -0.72
    WI
    -0.72
     Hearthstone
    -0.70
    resso
    -0.68
     Mighty
    -0.68
     Len
    -0.68
    GMT
    -0.68
     BW
    -0.66
     AMC
    -0.66
    POSITIVE LOGITS
     Raqqa
    2.08
     Perkins
    2.00
     Robertson
    1.92
     Parsons
    1.52
     Tanner
    1.36
     Pett
    1.32
     Olson
    1.28
    qqa
    1.18
     Cout
    1.16
     Pag
    1.04
    Activations Density 0.053%

    No Known Activations