© 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. 9207
    Prev
    Next
    INDEX
    Explanations

    phrases related to tasks or actions that can be done or avoided without a specific requirement or action

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of doing something without additional requirement or consequence

    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
     Vald
    -0.73
     Christy
    -0.70
    nia
    -0.64
    undrum
    -0.63
    姫
    -0.63
    soon
    -0.60
    oret
    -0.60
     Delta
    -0.59
     Rodrigo
    -0.58
     Kinnikuman
    -0.57
    POSITIVE LOGITS
     oneself
    0.73
     necessarily
    0.66
     interruption
    0.64
    zzle
    0.63
    epad
    0.63
     explicitly
    0.62
     whatsoever
    0.61
     slightest
    0.60
     manually
    0.60
    endish
    0.59
    Activations Density 0.088%

    No Known Activations