© 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. 6-RES-JB
    11. 3524
    Prev
    Next
    INDEX
    Explanations

    words and phrases that end with 'x'

    oai_token-act-pair · gpt-3.5-turbo

    references to the letter "x" or the use of "x" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    £ı
    -0.74
     Pru
    -0.73
    assetsadobe
    -0.71
     antioxid
    -0.70
     Courage
    -0.68
     cannabin
    -0.66
    à¤
    -0.65
     behavi
    -0.65
     kinderg
    -0.65
     Kirin
    -0.64
    POSITIVE LOGITS
    odus
    1.13
    posure
    1.12
    ample
    1.11
    actly
    1.10
    posed
    1.09
    imity
    1.08
    press
    1.08
    avier
    1.07
    aminer
    1.06
    ercise
    1.04
    Activations Density 0.032%

    No Known Activations