© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1632
    Prev
    Next
    INDEX
    Explanations

    the concept of possession or ownership

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "possess" and its variations

    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
    RFC
    -0.75
     externalToEVAOnly
    -0.63
    bank
    -0.63
    ser
    -0.63
    Reply
    -0.59
     Dough
    -0.58
     laundering
    -0.57
    cas
    -0.57
    MQ
    -0.56
     rule
    -0.56
    POSITIVE LOGITS
     possession
    0.96
    ively
    0.93
    ivity
    0.92
    iveness
    0.89
    ives
    0.85
    sburg
    0.83
    isance
    0.82
    IVE
    0.81
    ive
    0.81
    ments
    0.79
    Activations Density 0.024%

    No Known Activations