© 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. 8-RES-JB
    11. 7636
    Prev
    Next
    INDEX
    Explanations

    situations or actions involving resistance or protection against various challenges and threats

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to resistance and protection against various forms of attack or adversity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Shares
    -0.64
    Aid
    -0.63
    REL
    -0.62
    aughtered
    -0.62
    PDATED
    -0.60
    ithe
    -0.60
    Chart
    -0.59
    jong
    -0.59
    ware
    -0.58
    vale
    -0.58
    POSITIVE LOGITS
     onslaught
    1.28
     pressures
    1.11
     adversity
    1.08
     encro
    1.05
     influx
    0.92
     pitfalls
    0.92
     intrusion
    0.91
     whims
    0.91
     wrath
    0.91
     invaders
    0.91
    Activations Density 0.819%

    No Known Activations