© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 15686
    Prev
    Next
    INDEX
    Explanations

    phrases related to international relations and conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to international relations and conflicts

    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
     Strauss
    -0.63
     Gi
    -0.60
     Franch
    -0.60
     Blanc
    -0.58
     Guatem
    -0.58
     Tib
    -0.58
     Tag
    -0.57
     Protective
    -0.57
     Lad
    -0.57
    ãĤĮ
    -0.56
    POSITIVE LOGITS
    htaking
    0.72
    animous
    0.72
    adeon
    0.71
    agonists
    0.63
    omers
    0.63
    agonist
    0.61
    Ĥ¬
    0.61
    vernment
    0.59
    uple
    0.59
     SNP
    0.57
    Activations Density 0.327%

    No Known Activations