© 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. 2-RES-JB
    11. 1866
    Prev
    Next
    INDEX
    Explanations

    phrases describing uniqueness or contrast

    oai_token-act-pair · gpt-3.5-turbo

    phrases that compare something as being distinct or different from others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idates
    -0.69
    aid
    -0.65
    hiba
    -0.64
    acia
    -0.63
    ells
    -0.63
    elfare
    -0.63
    iola
    -0.62
    aled
    -0.62
    anut
    -0.62
     Annotations
    -0.61
    POSITIVE LOGITS
    lihood
    1.49
    liest
    0.93
     ours
    0.82
     minded
    0.80
    prising
    0.80
    minded
    0.79
    lier
    0.73
     chronological
    0.70
    eatures
    0.69
     brill
    0.69
    Activations Density 0.009%

    No Known Activations