© 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. 10-RES-JB
    11. 6749
    Prev
    Next
    INDEX
    Explanations

    words related to encryption keys

    oai_token-act-pair · gpt-3.5-turbo

    references to cryptographic keys and key management concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ALLY
    -0.66
    ¬¼
    -0.62
     Fif
    -0.62
     Poe
    -0.61
     Brig
    -0.61
     PHOTO
    -0.60
     Paula
    -0.60
     Compl
    -0.59
     Pamela
    -0.58
    ICAN
    -0.58
    POSITIVE LOGITS
    stroke
    1.56
    chain
    1.37
    stro
    1.30
    pad
    1.27
    bind
    1.27
    */(
    1.26
    chains
    1.25
    hole
    1.22
    stone
    1.21
    word
    1.20
    Activations Density 0.025%

    No Known Activations