© 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. 12247
    Prev
    Next
    INDEX
    Explanations

    numeric dates in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol

    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
     guiActiveUnfocused
    -0.88
    OTOS
    -0.64
     Farming
    -0.63
     laundry
    -0.63
     publicity
    -0.62
     discrep
    -0.62
    ensical
    -0.62
     scatter
    -0.62
     Libyan
    -0.61
     tremend
    -0.61
    POSITIVE LOGITS
    Į
    0.90
    /
    0.90
    ¹
    0.89
    į
    0.84
    dro
    0.84
    ¬
    0.81
    §
    0.80
    pillar
    0.79
    ħ
    0.78
    £
    0.78
    Activations Density 0.202%

    No Known Activations