© 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. 7072
    Prev
    Next
    INDEX
    Explanations

    abstract concepts or ideas

    oai_token-act-pair · gpt-3.5-turbo

    phrases that begin with "the idea of."

    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
    ndum
    -0.68
    heast
    -0.66
    lake
    -0.65
     Ago
    -0.65
     ILCS
    -0.65
    eworthy
    -0.65
    roads
    -0.63
    ificant
    -0.62
    DF
    -0.62
    major
    -0.61
    POSITIVE LOGITS
    ually
    1.21
     moot
    0.87
     idea
    0.81
    atical
    0.81
    atics
    0.80
    urally
    0.74
    uitive
    0.74
    matic
    0.73
    ual
    0.71
    yout
    0.71
    Activations Density 0.027%

    No Known Activations