© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 10477
    Prev
    Next
    INDEX
    Explanations

    mentions of announcements or new launches

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a sense of collective involvement or presence

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

    No Comments

    Negative Logits
    ItemThumbnailImage
    -0.84
    cum
    -0.78
    lie
    -0.72
    soever
    -0.70
    âĵĺ
    -0.67
    iae
    -0.66
    —-
    -0.66
    lio
    -0.65
    rouse
    -0.61
    rone
    -0.60
    POSITIVE LOGITS
     OPEN
    0.68
     Open
    0.58
     Closing
    0.57
     stocked
    0.57
     edited
    0.57
    resa
    0.57
     Honor
    0.57
     Horus
    0.56
     Background
    0.56
     hereby
    0.56
    Activations Density 0.431%

    No Known Activations