© 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. 10-RES-JB
    11. 1458
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations, especially those containing the letter 'q'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "q" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lauder
    -0.60
     savior
    -0.60
    ################
    -0.60
     lav
    -0.58
     regenerate
    -0.58
     orche
    -0.58
     cheers
    -0.58
     revolving
    -0.57
    é¾įå
    -0.56
     regress
    -0.56
    POSITIVE LOGITS
    iao
    1.05
    aeda
    1.05
    eer
    0.98
    iu
    0.98
    een
    0.94
    dn
    0.94
    iang
    0.93
    eh
    0.91
    eus
    0.91
    eq
    0.90
    Activations Density 0.020%

    No Known Activations