© 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. 7-RES-JB
    11. 11711
    Prev
    Next
    INDEX
    Explanations

    Although statements indicating a contrast between two pieces of information

    oai_token-act-pair · gpt-3.5-turbo

    instances of transitional phrases or conjunctions indicating contrast

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tnc
    -0.67
    oiler
    -0.63
    bas
    -0.63
    lees
    -0.62
    Jew
    -0.62
    ilver
    -0.61
     srfAttach
    -0.61
    ×ķ
    -0.60
    anut
    -0.60
     ÙĪ
    -0.59
    POSITIVE LOGITS
    ts
    1.03
     acknowledging
    1.02
     technically
    0.97
     conced
    0.83
     initially
    0.82
     admittedly
    0.78
     researching
    0.72
    tons
    0.71
     browsing
    0.69
     normally
    0.68
    Activations Density 0.054%

    No Known Activations