© 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. 10-RES-JB
    11. 3182
    Prev
    Next
    INDEX
    Explanations

    phrases related to various social interactions or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrasal representations of identity or existence statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Skydragon
    -0.71
     Tek
    -0.70
     Tid
    -0.70
     mathemat
    -0.68
     Wer
    -0.68
     Objective
    -0.66
     seiz
    -0.65
     fortun
    -0.65
     Sok
    -0.64
     Targ
    -0.63
    POSITIVE LOGITS
    Ļ
    1.60
    ª
    1.39
    ħ
    1.33
    ¬
    1.32
    ĸ
    1.30
    ¤
    1.30
    Ķ
    1.29
    ¡
    1.23
    Ĵ
    1.21
    «
    1.21
    Activations Density 0.224%

    No Known Activations