© 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. 9861
    Prev
    Next
    INDEX
    Explanations

    words related to opposition or contradiction

    oai_token-act-pair · gpt-3.5-turbo

    references to 'counter' in various contexts

    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
     ABE
    -0.79
     Forge
    -0.76
     Tornado
    -0.74
     Known
    -0.70
    doms
    -0.70
     Stras
    -0.68
     Slime
    -0.68
     Roche
    -0.67
     Tycoon
    -0.65
     Cursed
    -0.65
    POSITIVE LOGITS
    measures
    1.27
    balance
    1.18
    intuitive
    1.18
    attack
    1.15
    intelligence
    1.12
    offensive
    1.08
    ror
    1.06
    fact
    1.03
    counter
    1.03
    balanced
    1.01
    Activations Density 0.024%

    No Known Activations