© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 8647
    Prev
    Next
    INDEX
    Explanations

    verbs related to taking action to fix, correct, or improve a situation

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to restoration or recovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gom
    -0.76
    kson
    -0.75
    kers
    -0.67
    fork
    -0.65
    ertodd
    -0.64
    gerald
    -0.63
    aned
    -0.63
    owler
    -0.63
    Plot
    -0.62
    iri
    -0.62
    POSITIVE LOGITS
     sanity
    0.96
     harmony
    0.91
     balance
    0.89
     equilibrium
    0.88
     composure
    0.86
    parency
    0.82
     calm
    0.80
     stability
    0.80
     dignity
    0.79
     tranqu
    0.78
    Activations Density 0.064%

    No Known Activations