© 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. 5156
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "We"

    oai_token-act-pair · gpt-3.5-turbo

    collective pronouns indicating group actions or sentiments

    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
     UD
    -0.72
     gratification
    -0.67
     totality
    -0.67
     LSD
    -0.66
    cum
    -0.65
     quo
    -0.65
     otherwise
    -0.61
     srfAttach
    -0.61
     resting
    -0.59
     Wikipedia
    -0.57
    POSITIVE LOGITS
    ldon
    1.21
    bley
    1.18
    eks
    1.16
    ird
    1.12
    akening
    1.08
    bsite
    1.08
    alth
    1.07
    've
    1.07
    zbollah
    1.06
    're
    1.04
    Activations Density 0.091%

    No Known Activations