© 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. 7-RES-JB
    11. 23746
    Prev
    Next
    INDEX
    Explanations

    words related to restoration or bringing back something that was lost or damaged

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "restore" and its variations in various contexts related to recovery or reinstatement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gom
    -0.77
    kers
    -0.77
    QB
    -0.76
    gerald
    -0.71
    rics
    -0.70
    Die
    -0.67
    SON
    -0.63
    wer
    -0.63
    KER
    -0.63
    ks
    -0.63
    POSITIVE LOGITS
     vig
    0.78
     composure
    0.78
    itial
    0.77
     restoration
    0.76
     restores
    0.75
     restore
    0.74
     harmony
    0.72
     sanity
    0.72
    parency
    0.69
    balance
    0.69
    Activations Density 0.036%

    No Known Activations