© 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. 1-RES-JB
    11. 3740
    Prev
    Next
    INDEX
    Explanations

    names containing the string 'Dob'

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names or proper nouns, particularly those containing "Dob."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Peel
    -0.81
    ipop
    -0.73
    soType
    -0.73
    coat
    -0.70
     Paste
    -0.70
     Panc
    -0.69
    =]
    -0.67
    icrobial
    -0.67
    insula
    -0.65
     Immunity
    -0.64
    POSITIVE LOGITS
     Dob
    1.03
    borg
    0.94
    sonian
    0.88
    rolet
    0.86
    kos
    0.79
    kie
    0.79
    DCS
    0.76
    gged
    0.74
    dos
    0.73
    lington
    0.72
    Activations Density 0.019%

    No Known Activations