© 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. 2-RES-JB
    11. 18760
    Prev
    Next
    INDEX
    Explanations

    words with the prefix "re-" indicating repetition or restoration of an action

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "re-," indicating words related to actions that are being repeated or revisited

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nieto
    -0.77
     Phar
    -0.74
     Everywhere
    -0.70
     Ideal
    -0.68
     Institution
    -0.67
     Achievements
    -0.65
     Invisible
    -0.64
     Pebble
    -0.64
     Fifth
    -0.64
     Tong
    -0.64
    POSITIVE LOGITS
    becca
    1.12
    forestation
    0.96
    integ
    0.96
    authorized
    0.96
    ordered
    0.95
    verend
    0.94
    interpret
    0.92
    uph
    0.92
    claimer
    0.91
    formation
    0.91
    Activations Density 0.025%

    No Known Activations