© 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. 8-RES-JB
    11. 3096
    Prev
    Next
    INDEX
    Explanations

    verbs indicating causation or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate causation or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atching
    -0.59
    entric
    -0.58
    aves
    -0.56
    afort
    -0.56
    arer
    -0.55
    iling
    -0.55
    Fram
    -0.54
    ature
    -0.54
    inen
    -0.53
    ZI
    -0.52
    POSITIVE LOGITS
     inex
    0.87
     nowhere
    0.82
    ãĥĥãĥī
    0.80
    gers
    0.79
    uez
    0.75
    -+
    0.74
     inevitably
    0.73
    wcs
    0.71
    iments
    0.70
     us
    0.69
    Activations Density 0.047%

    No Known Activations