© 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. 18448
    Prev
    Next
    INDEX
    Explanations

    text snippets that emphasize the significance of certain points or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the significance of certain points or concepts

    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
    thur
    -0.74
    iche
    -0.70
    sil
    -0.67
    othy
    -0.66
    appro
    -0.64
     Lyme
    -0.63
    agra
    -0.63
    olog
    -0.63
    jab
    -0.63
    ye
    -0.62
    POSITIVE LOGITS
     importantly
    0.89
    theless
    0.86
    NESS
    0.86
    terday
    0.84
     impacting
    0.79
    xual
    0.76
     distingu
    0.72
     proble
    0.71
     impacted
    0.70
    atility
    0.68
    Activations Density 0.008%

    No Known Activations