© 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. 20238
    Prev
    Next
    INDEX
    Explanations

    phrases related to being restricted or confined

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "locked" 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
    issance
    -0.94
    lus
    -0.81
    resso
    -0.81
     Lynd
    -0.78
    annis
    -0.75
    lication
    -0.75
    anasia
    -0.71
    mony
    -0.69
    ciation
    -0.68
    enegger
    -0.67
    POSITIVE LOGITS
    picking
    1.01
    heed
    0.90
    door
    0.89
    locked
    0.87
    lock
    0.87
     locked
    0.84
    locking
    0.84
     lock
    0.81
     horns
    0.80
     doors
    0.79
    Activations Density 0.017%

    No Known Activations