© 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. 3-RES-JB
    11. 3444
    Prev
    Next
    INDEX
    Explanations

    phrases related to security measures or names/terms related to locks

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "lock" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issance
    -0.77
    LV
    -0.71
    resso
    -0.71
    opausal
    -0.68
    aukee
    -0.66
     Eleven
    -0.66
    schild
    -0.65
    OTAL
    -0.64
    PsyNetMessage
    -0.64
    icz
    -0.64
    POSITIVE LOGITS
    picking
    1.30
    heed
    1.11
    pick
    1.06
    lear
    0.95
    lock
    0.91
    downs
    0.90
    door
    0.89
    yer
    0.85
    creen
    0.85
    down
    0.83
    Activations Density 0.014%

    No Known Activations