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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RES-JB
    6. 5401
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific type of weapon - "cluster bombs"

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of clusters, particularly in a scientific or military context

    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
    Ö¼
    -0.76
    hran
    -0.74
    azeera
    -0.70
    ODUCT
    -0.68
    toc
    -0.66
    ãĤ®
    -0.65
    inburgh
    -0.64
    orial
    -0.64
    inez
    -0.64
    estamp
    -0.63
    POSITIVE LOGITS
    fuck
    1.24
     bom
    1.07
    mates
    0.89
    usters
    0.85
     cluster
    0.83
     clusters
    0.76
     mun
    0.72
     clustered
    0.69
    uster
    0.68
     munitions
    0.68
    Activations Density 0.028%

    No Known Activations