© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11058
    Prev
    Next
    INDEX
    Explanations

    personal references, particularly the use of "me" and "myself" in text

    oai_token-act-pair · gpt-3.5-turbo

    references to personal identification and shared experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     equival
    -0.72
     Provided
    -0.65
    WAR
    -0.64
    boxing
    -0.63
     legality
    -0.63
     truce
    -0.63
     feasibility
    -0.62
     arrang
    -0.61
     violation
    -0.61
     shipment
    -0.60
    POSITIVE LOGITS
     readers
    0.78
     who
    0.75
     whom
    0.74
    llah
    0.74
    izer
    0.74
    bies
    0.71
     addicted
    0.68
     myself
    0.68
    odi
    0.68
    atell
    0.67
    Activations Density 0.106%

    No Known Activations