© 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. 9407
    Prev
    Next
    INDEX
    Explanations

    keywords related to removing something or someone

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to eliminating or removing something

    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
    orld
    -0.67
    anwhile
    -0.64
    acs
    -0.63
    Kind
    -0.60
    ortment
    -0.58
     Indust
    -0.57
    Leader
    -0.57
     therap
    -0.56
    fair
    -0.56
    acement
    -0.56
    POSITIVE LOGITS
     unnecessary
    0.93
     unwanted
    0.89
     duplicate
    0.86
     stray
    0.81
     traces
    0.80
    ively
    0.79
     distractions
    0.78
     weeds
    0.74
     pesky
    0.74
     any
    0.73
    Activations Density 0.139%

    No Known Activations