© 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. 2-RES-JB
    11. 23903
    Prev
    Next
    INDEX
    Explanations

    mixtures or combinations of different elements

    oai_token-act-pair · gpt-3.5-turbo

    references to mixtures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĻĤ
    -0.95
    orth
    -0.75
    ond
    -0.73
     Passage
    -0.72
     Borders
    -0.71
    £
    -0.69
    ighth
    -0.69
    yright
    -0.69
    ¥ŀ
    -0.67
    stra
    -0.67
    POSITIVE LOGITS
     mixture
    1.18
     mixes
    1.03
     blends
    0.96
     mix
    0.95
     conco
    0.89
     blend
    0.87
     blending
    0.79
     amalg
    0.77
     mixing
    0.76
    ichick
    0.75
    Activations Density 0.012%

    No Known Activations