© 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. 0-RES-JB
    11. 5402
    Prev
    Next
    INDEX
    Explanations

    mentions of the concept of "private."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "private" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etta
    -0.86
    asso
    -0.83
    hes
    -0.82
    pedia
    -0.71
    uph
    -0.68
    eny
    -0.67
    onent
    -0.67
    actic
    -0.66
    burst
    -0.65
    !/
    -0.65
    POSITIVE LOGITS
     private
    3.58
    private
    3.00
    Private
    2.72
     Private
    2.61
     privately
    2.30
     public
    1.73
     privat
    1.56
     confidential
    1.44
    public
    1.43
     personal
    1.42
    Activations Density 0.024%

    No Known Activations