© 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. 7344
    Prev
    Next
    INDEX
    Explanations

    references to various locations or regions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "across" in various contexts

    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
    nery
    -0.81
    nel
    -0.71
    IZ
    -0.69
    etic
    -0.65
    zel
    -0.62
    anza
    -0.62
    nas
    -0.62
     diseng
    -0.60
     coincidence
    -0.60
    oka
    -0.59
    POSITIVE LOGITS
    roads
    1.09
    ĨĴ
    0.90
     disciplines
    0.84
    urst
    0.83
    cedented
    0.81
    artisan
    0.81
    scl
    0.79
    soType
    0.79
    atform
    0.76
    Ĥª
    0.75
    Activations Density 0.025%

    No Known Activations