© 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 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. 8-RES-JB
    11. 3886
    Prev
    Next
    INDEX
    Explanations

    various combinations or mixtures of elements

    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 @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Skies
    -0.67
    osponsors
    -0.66
    Attempts
    -0.65
     Passage
    -0.63
     Absent
    -0.63
    hood
    -0.63
    Constructed
    -0.62
     captcha
    -0.61
     Borders
    -0.61
     Sabha
    -0.59
    POSITIVE LOGITS
    xual
    0.98
    mix
    0.96
    lr
    0.91
    ologist
    0.89
    Mix
    0.82
     mixes
    0.81
    oly
    0.80
    tec
    0.80
    lins
    0.77
    opl
    0.76
    Activations Density 0.029%

    No Known Activations