© 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. 0-RES-JB
    11. 12730
    Prev
    Next
    INDEX
    Explanations

    words containing "ank" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "blank" or similar sounding words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reflected
    -0.70
     reflective
    -0.67
     perpet
    -0.66
     proportional
    -0.65
     variance
    -0.65
     reversible
    -0.64
     mirrors
    -0.63
     repl
    -0.63
     monitors
    -0.62
     repe
    -0.61
    POSITIVE LOGITS
    ank
    4.46
    anks
    2.44
    anked
    2.24
    anking
    2.21
    ANK
    2.19
    anky
    1.89
    anka
    1.73
    anke
    1.38
    inks
    1.27
    unk
    1.27
    Activations Density 0.014%

    No Known Activations