© 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. 7221
    Prev
    Next
    INDEX
    Explanations

    words related to the anatomy of the eye

    oai_token-act-pair · gpt-3.5-turbo

    the word "cor" and its variations in different contexts, indicating a focus on specific terminologies or references related to core concepts

    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
    lihood
    -0.81
    endor
    -0.81
    UME
    -0.77
    éĹĺ
    -0.73
     Disorder
    -0.73
    hirt
    -0.72
     Rasmussen
    -0.71
     Merrill
    -0.71
    terday
    -0.68
    UGE
    -0.66
    POSITIVE LOGITS
    nered
    1.09
    fman
    1.00
    vette
    0.99
    ros
    0.94
    nea
    0.91
    ruption
    0.90
    rup
    0.86
    neys
    0.84
    alled
    0.83
    bara
    0.82
    Activations Density 0.005%

    No Known Activations