© 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. 1081
    Prev
    Next
    INDEX
    Explanations

    phrases describing the best or highest level possible in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of achieving the "best" or "greatest" outcomes or benefits

    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
    bane
    -0.80
    yer
    -0.80
    gar
    -0.77
    masters
    -0.76
    oute
    -0.73
    wa
    -0.73
    ithing
    -0.72
    wood
    -0.72
    dog
    -0.72
    wan
    -0.72
    POSITIVE LOGITS
    Versions
    0.76
     Parenthood
    0.75
    escape
    0.74
    TPPStreamerBot
    0.71
    iary
    0.71
     selves
    0.70
     dstg
    0.70
    arial
    0.68
    cffffcc
    0.66
     surv
    0.64
    Activations Density 0.025%

    No Known Activations