© 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. 16063
    Prev
    Next
    INDEX
    Explanations

    instances of actions related to possession or control over objects

    oai_token-act-pair · gpt-3.5-turbo

    references to personal pronouns and terms indicating presence or availability

    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
    WARD
    -0.86
     Cosponsors
    -0.85
    advertising
    -0.73
    ados
    -0.72
    could
    -0.66
    wards
    -0.64
     [+]
    -0.64
    ATIVE
    -0.62
    itsch
    -0.62
    ugh
    -0.60
    POSITIVE LOGITS
     installed
    1.21
     pegged
    1.12
     ready
    1.12
     handy
    1.05
     lined
    1.02
     surg
    0.98
     implanted
    0.98
     hooked
    0.97
     pinned
    0.96
     nailed
    0.94
    Activations Density 0.298%

    No Known Activations