© 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. 10-RES-JB
    11. 5097
    Prev
    Next
    INDEX
    Explanations

    phrases related to possessing, featuring, or highlighting something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of ownership and individuality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atform
    -0.89
    Registration
    -0.77
    thood
    -0.73
     )]
    -0.73
    Alert
    -0.73
    ntil
    -0.72
    ACP
    -0.71
    IB
    -0.69
    ¿
    -0.68
    vertisement
    -0.68
    POSITIVE LOGITS
     quirks
    1.55
     strengths
    1.52
     drawbacks
    1.34
     weaknesses
    1.33
     advantages
    1.32
     flaws
    1.30
     faults
    1.29
     merits
    1.27
     idiosyncr
    1.24
     shortcomings
    1.20
    Activations Density 0.125%

    No Known Activations