Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 17351
    Prev
    Next
    INDEX
    Explanations

    concepts related to threats and intimidation

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "threat."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mys
    -0.91
    ilts
    -0.82
    algia
    -0.81
    val
    -0.81
    iked
    -0.77
    urgy
    -0.76
    cle
    -0.74
    ann
    -0.71
    rain
    -0.71
    gart
    -0.70
    POSITIVE LOGITS
     threaten
    1.13
     threatens
    1.11
     threats
    0.98
     endanger
    0.94
     threatened
    0.92
     threatening
    0.91
     challeng
    0.91
     Threat
    0.91
    threat
    0.90
     menacing
    0.85
    Activations Density 0.006%

    No Known Activations