© 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. 8-RES-JB
    11. 17178
    Prev
    Next
    INDEX
    Explanations

    words related to political events and decisions

    oai_token-act-pair · gpt-3.5-turbo

    topics related to war and conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.78
    Nusra
    -0.66
    Iterator
    -0.63
    */(
    -0.63
     Faction
    -0.62
    Cooldown
    -0.60
     Canon
    -0.60
     Garmin
    -0.60
     Folder
    -0.59
     Siri
    -0.58
    POSITIVE LOGITS
    Ħ¢
    0.73
    itialized
    0.60
     legitimately
    0.59
     entire
    0.59
     humankind
    0.58
    orld
    0.57
     nation
    0.56
     horrend
    0.56
    cember
    0.56
     rightful
    0.55
    Activations Density 1.456%

    No Known Activations