© 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. 1-RES-JB
    11. 16815
    Prev
    Next
    INDEX
    Explanations

    references to geopolitical events and conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific nationalities or geopolitical entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OVA
    -0.43
    Discussion
    -0.37
    VALUE
    -0.36
    é¾įå
    -0.34
    idated
    -0.34
     suffice
    -0.34
    acebook
    -0.34
    ãĥİ
    -0.34
    031
    -0.33
    Notable
    -0.32
    POSITIVE LOGITS
    terness
    0.42
     DRAGON
    0.39
    gae
    0.35
     largeDownload
    0.35
    hap
    0.34
    sych
    0.33
    reb
    0.33
    bender
    0.33
    ANS
    0.33
     Marijuana
    0.33
    Activations Density 3.283%

    No Known Activations