© 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. 12768
    Prev
    Next
    INDEX
    Explanations

    phrases related to protection and defense

    oai_token-act-pair · gpt-3.5-turbo

    terms related to protection or defense against various threats

    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
    tein
    -0.83
     Surv
    -0.72
     Redemption
    -0.65
     Mile
    -0.63
     compensated
    -0.62
     Cop
    -0.61
     segregated
    -0.59
    å¦
    -0.59
    ¢
    -0.59
     aborted
    -0.57
    POSITIVE LOGITS
     onslaught
    1.51
     threats
    1.10
     intrusion
    1.08
     encro
    1.03
     barrage
    1.03
     pressures
    1.02
     threat
    1.00
     influx
    0.98
    attacks
    0.97
     whims
    0.96
    Activations Density 0.507%

    No Known Activations