© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 15512
    Prev
    Next
    INDEX
    Explanations

    phrases related to abstract concepts or opinions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that begin with "something."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fight
    -0.73
    ortex
    -0.71
    sein
    -0.69
    sie
    -0.68
    termin
    -0.68
     Telecommunications
    -0.67
    shock
    -0.66
    say
    -0.64
     Transcript
    -0.63
    DOS
    -0.63
    POSITIVE LOGITS
     else
    1.25
    Else
    1.00
     akin
    0.88
     entirely
    0.80
     Else
    0.78
     resembling
    0.77
     intangible
    0.75
     unimaginable
    0.72
     shameful
    0.72
     we
    0.71
    Activations Density 0.041%

    No Known Activations