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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 5270
    Prev
    Next
    INDEX
    Explanations

    references to art and historical artifacts in museums

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of historical artifacts and their locations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStreamFrame
    -1.00
    twitch
    -0.92
     thrott
    -0.90
     Mbps
    -0.88
    amacare
    -0.86
     twitch
    -0.83
    gamer
    -0.81
     throttle
    -0.79
     Lyft
    -0.79
    Mbps
    -0.76
    POSITIVE LOGITS
     museum
    1.72
     museums
    1.64
     archaeologists
    1.59
     archaeological
    1.57
     excav
    1.48
     excavation
    1.46
     sculptures
    1.44
     Museum
    1.42
     Archae
    1.42
     treasures
    1.40
    Activations Density 0.931%

    No Known Activations