© 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. 6-RES-JB
    11. 13647
    Prev
    Next
    INDEX
    Explanations

    instances of the word "possession."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of possession-related offenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    htt
    -0.70
    MQ
    -0.67
     externalToEVAOnly
    -0.64
    mitt
    -0.63
    bank
    -0.62
    prep
    -0.61
    Redd
    -0.61
     resc
    -0.61
    ser
    -0.61
    marg
    -0.60
    POSITIVE LOGITS
    ivity
    1.01
     possession
    0.94
    ership
    0.93
    ive
    0.89
    iveness
    0.88
    ibility
    0.88
    iture
    0.86
    ession
    0.85
    essor
    0.85
    alogue
    0.84
    Activations Density 0.036%

    No Known Activations