© 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. 13790
    Prev
    Next
    INDEX
    Explanations

    phrases related to quantity or number

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating quantity or prevalence

    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
    ukong
    -0.66
    emonium
    -0.66
    rawdownloadcloneembedreportprint
    -0.65
    =-=-=-=-=-=-=-=-
    -0.63
    },{"
    -0.60
    bye
    -0.60
    herty
    -0.60
    Quote
    -0.60
    66666666
    -0.58
    oken
    -0.58
    POSITIVE LOGITS
     notably
    1.10
     preferring
    1.10
     consisting
    1.07
     originating
    1.03
     comprising
    1.03
     specializing
    1.01
     involving
    1.01
     citing
    0.99
     claiming
    0.98
     resembling
    0.96
    Activations Density 0.078%

    No Known Activations