© 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. 6-RES-JB
    11. 21917
    Prev
    Next
    INDEX
    Explanations

    events and occurrences followed by a specific period of time

    oai_token-act-pair · gpt-3.5-turbo

    references to events involving conflict or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ministic
    -0.65
    Ability
    -0.65
    osc
    -0.61
     Simulator
    -0.61
    omorph
    -0.58
    Engine
    -0.58
    Zip
    -0.57
     Programming
    -0.57
     Zombies
    -0.57
     Interface
    -0.55
    POSITIVE LOGITS
     controversy
    0.99
     contentious
    0.93
     controversies
    0.92
     controvers
    0.92
     embattled
    0.91
     controversial
    0.88
     outspoken
    0.85
     hotly
    0.84
     embroiled
    0.80
     crackdown
    0.77
    Activations Density 1.489%

    No Known Activations