© 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. 9-RES-JB
    11. 5445
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing individual ownership or uniqueness

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing individuality and personal ownership

    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
    IB
    -0.82
    ISON
    -0.81
    nc
    -0.80
    Alert
    -0.79
    iron
    -0.78
    atform
    -0.77
    ntil
    -0.76
    ograph
    -0.76
    ¿
    -0.75
    spection
    -0.74
    POSITIVE LOGITS
     strengths
    1.32
     quirks
    1.24
     advantages
    1.11
     idiosyncr
    1.10
     weaknesses
    1.09
     distinct
    1.07
     drawbacks
    1.06
     repertoire
    1.06
     unique
    1.04
     tendency
    1.03
    Activations Density 0.184%

    No Known Activations