© 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. 8-RES-JB
    11. 10363
    Prev
    Next
    INDEX
    Explanations

    terms related to possession or ownership

    oai_token-act-pair · gpt-3.5-turbo

    references to the ownership and consequences associated with various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Enable
    -0.78
    ILE
    -0.77
    Yan
    -0.74
    imal
    -0.74
    inet
    -0.74
    ****
    -0.74
    IF
    -0.74
    IFIED
    -0.73
    WHO
    -0.73
    UC
    -0.72
    POSITIVE LOGITS
     attendant
    1.38
     allies
    1.28
     associated
    1.15
     il
    1.14
     successors
    1.14
     accompanying
    1.11
     surroundings
    1.10
     affiliates
    1.09
     derivatives
    1.09
     heirs
    1.09
    Activations Density 0.087%

    No Known Activations