© 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. 4-RES-JB
    11. 7096
    Prev
    Next
    INDEX
    Explanations

    phrases related to platitudes and specific names like "Plat" or "polyg"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to platitudes and discussions about relationships, including both polyamory and monogamy

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

    No Comments

    Negative Logits
    PRES
    -0.77
    shapeshifter
    -0.76
    study
    -0.67
    Interstitial
    -0.65
    Il
    -0.64
    Lee
    -0.63
    Leary
    -0.62
    CVE
    -0.60
    TIME
    -0.59
     Estimates
    -0.59
    POSITIVE LOGITS
    onic
    1.20
    itudes
    1.16
    itude
    1.05
    itud
    1.02
    yp
    1.02
     plat
    1.01
     Plat
    0.92
    imes
    0.92
    plain
    0.87
    atform
    0.85
    Activations Density 0.017%

    No Known Activations