© 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. 11-RES-JB
    11. 4156
    Prev
    Next
    INDEX
    Explanations

    words related to encryption and security, particularly focusing on electronic keys

    oai_token-act-pair · gpt-3.5-turbo

    references to keys or key-related concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bett
    -0.89
     includ
    -0.85
     millenn
    -0.82
     resil
    -0.82
     spr
    -0.74
    ̶
    -0.73
    Tex
    -0.73
     horizontally
    -0.72
    atu
    -0.71
     Fell
    -0.71
    POSITIVE LOGITS
     Key
    2.32
    key
    2.19
    Key
    2.11
     KEY
    2.06
     Keys
    1.96
    Keys
    1.95
    KEY
    1.93
     key
    1.85
    keys
    1.82
     keys
    1.73
    Activations Density 0.178%

    No Known Activations