© 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. 3-RES-JB
    11. 15081
    Prev
    Next
    INDEX
    Explanations

    phrases with opposing viewpoints or actions

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "but" indicating contrast or opposition in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nce
    -0.66
    resa
    -0.63
    tnc
    -0.60
    mary
    -0.60
    vance
    -0.59
    ammu
    -0.59
    lish
    -0.58
    uto
    -0.58
    venue
    -0.58
    ogical
    -0.58
    POSITIVE LOGITS
    tons
    1.15
    chery
    1.04
     alas
    0.87
    chers
    0.86
     nevertheless
    0.85
    tered
    0.80
     luckily
    0.80
     fortunately
    0.79
     nonetheless
    0.79
    ler
    0.76
    Activations Density 0.105%

    No Known Activations