© 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. 4-RES-JB
    11. 4033
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating opposition or contrast

    oai_token-act-pair · gpt-3.5-turbo

    the term "opposite" in various contexts

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

    No Comments

    Negative Logits
    atche
    -0.84
    lished
    -0.81
    zeb
    -0.78
    ondon
    -0.74
    abiding
    -0.74
    zinski
    -0.73
    ourn
    -0.72
    ule
    -0.72
    uay
    -0.71
    ashington
    -0.71
    POSITIVE LOGITS
     sides
    0.83
     opposite
    0.81
    osite
    0.80
     sexes
    0.79
     side
    0.76
    ICE
    0.75
     oppos
    0.75
     twins
    0.71
    etheless
    0.71
     sex
    0.70
    Activations Density 0.013%

    No Known Activations