© 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. 6-RES-JB
    11. 5055
    Prev
    Next
    INDEX
    Explanations

    personal pronouns related to collective human experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to "us" and "them" dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    egu
    -0.63
    hai
    -0.62
     Waiting
    -0.59
     ASA
    -0.58
    itton
    -0.58
    )].
    -0.57
     sometime
    -0.57
    ructose
    -0.57
     assembly
    -0.56
     BB
    -0.55
    POSITIVE LOGITS
     nor
    1.42
     whatsoever
    1.36
    nor
    1.01
     anymore
    0.99
     dime
    0.92
     necessarily
    0.89
     EVER
    0.85
     lasts
    0.84
     except
    0.83
    soever
    0.83
    Activations Density 0.151%

    No Known Activations