© 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. 4-RES-JB
    11. 4614
    Prev
    Next
    INDEX
    Explanations

    keywords related to mobile applications

    oai_token-act-pair · gpt-3.5-turbo

    references to applications or app-related topics

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

    No Comments

    Negative Logits
    terday
    -0.85
    ovych
    -0.69
     cigars
    -0.69
    warts
    -0.67
    Downloadha
    -0.67
     outdoors
    -0.67
     rods
    -0.64
     Protestant
    -0.63
    ãĥīãĥ©ãĤ´ãĥ³
    -0.62
     methyl
    -0.62
    POSITIVE LOGITS
    alach
    1.36
    ointment
    1.33
    reciation
    1.26
    ropri
    1.24
    rentices
    1.19
    earance
    1.18
    endix
    1.17
    ortion
    1.14
    arent
    1.14
    rehens
    1.13
    Activations Density 0.017%

    No Known Activations