© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 2770
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of lock or deadlock

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lock" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     RESP
    -0.70
     Di
    -0.68
     Param
    -0.66
     subsid
    -0.64
    Ô
    -0.63
     anth
    -0.61
     Fe
    -0.61
     Ré
    -0.61
     Pale
    -0.60
     derived
    -0.59
    POSITIVE LOGITS
    lock
    4.76
    locks
    3.46
    locked
    2.56
    LOCK
    2.37
    locking
    2.35
    Lock
    2.07
     lock
    1.59
     Lock
    1.56
     locks
    1.42
     locking
    1.27
    Activations Density 0.012%

    No Known Activations