© 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. 1-RES-JB
    11. 21563
    Prev
    Next
    INDEX
    Explanations

    keywords related to the term "ception"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ception" and its variations, indicating a focus on the topic of perception or related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     constituent
    -0.77
    hed
    -0.69
     comb
    -0.68
    hov
    -0.67
     reconc
    -0.66
     organizing
    -0.66
    osh
    -0.66
    accompan
    -0.65
     retri
    -0.65
     exped
    -0.64
    POSITIVE LOGITS
    ception
    1.50
    ceptions
    0.91
    ibility
    0.87
    yip
    0.79
    ISION
    0.78
     Detection
    0.76
    pedia
    0.76
    isexual
    0.76
    ibles
    0.75
    ISM
    0.75
    Activations Density 0.010%

    No Known Activations