© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 5759
    Prev
    Next
    INDEX
    Explanations

    mentions of possessive pronouns, specifically 'his'

    oai_token-act-pair · gpt-3.5-turbo

    references to possession or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itect
    -0.74
    amazon
    -0.68
    Trend
    -0.68
    FY
    -0.66
    ocument
    -0.66
     Unsure
    -0.66
    ablishment
    -0.65
     Compare
    -0.65
    igslist
    -0.63
    resh
    -0.63
    POSITIVE LOGITS
     own
    1.52
    panic
    1.20
     father
    1.00
     assailant
    0.99
     opponent
    0.98
     newfound
    0.93
     usual
    0.92
     favourite
    0.91
    sing
    0.91
     preferred
    0.90
    Activations Density 0.205%

    No Known Activations