© 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. 15825
    Prev
    Next
    INDEX
    Explanations

    words related to permanence and impermanence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to permanence or impermanence

    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
    anwhile
    -0.83
    wagen
    -0.79
     Valkyrie
    -0.73
     guiActiveUnfocused
    -0.69
    ãĥ¯ãĥ³
    -0.69
     CDs
    -0.67
    FactoryReloaded
    -0.67
    hare
    -0.64
     Ou
    -0.64
    creen
    -0.63
    POSITIVE LOGITS
    ishable
    1.23
    missible
    1.13
    manent
    1.10
    vious
    1.06
    mented
    0.89
    bably
    0.88
    iled
    0.88
    cept
    0.86
    ¥ŀ
    0.86
    ceivable
    0.84
    Activations Density 0.005%

    No Known Activations