© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 12986
    Prev
    Next
    INDEX
    Explanations

    the word "mix" occurring with different contexts and topics in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "mix" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pen
    -0.73
     Memorial
    -0.71
    vernment
    -0.64
     erected
    -0.64
     erection
    -0.63
    swer
    -0.63
    utherford
    -0.62
    arger
    -0.62
    hood
    -0.62
     Defenders
    -0.62
    POSITIVE LOGITS
     mix
    1.25
     mixes
    1.18
    mix
    1.15
    Mix
    1.02
    mble
    0.97
     Mix
    0.94
     mixture
    0.85
     mixing
    0.76
     blends
    0.75
     blend
    0.71
    Activations Density 0.010%

    No Known Activations