© 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. 11-RES-JB
    11. 7663
    Prev
    Next
    INDEX
    Explanations

    phrases related to routines and daily activities

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal experiences and routines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yourselves
    -1.06
    å°Ĩ
    -0.70
    Congratulations
    -0.67
    icipated
    -0.66
    tained
    -0.65
     breached
    -0.62
    intendent
    -0.61
     1943
    -0.61
     discredited
    -0.61
    è£ħ
    -0.60
    POSITIVE LOGITS
     my
    1.36
     myself
    1.35
     I
    1.09
     whenever
    0.98
     sometimes
    0.96
     haha
    0.96
    My
    0.91
    sometimes
    0.90
    I
    0.86
     mornings
    0.85
    Activations Density 0.652%

    No Known Activations