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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-RES-JB
    6. 3426
    Prev
    Next
    INDEX
    Explanations

    terms related to intimidation and coercion

    oai_token-act-pair · gpt-3.5-turbo

    references to intimidation and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    launch
    -0.87
    odes
    -0.86
    eem
    -0.81
    orah
    -0.79
    issue
    -0.77
    ourn
    -0.76
    ether
    -0.76
    haps
    -0.76
    empl
    -0.75
    ays
    -0.75
    POSITIVE LOGITS
     intimidation
    1.24
     intimidated
    1.23
     intimid
    1.17
     intimidate
    1.04
     intimidating
    0.91
     stalking
    0.88
     tactics
    0.87
     disadvant
    0.83
     retaliation
    0.78
     harassed
    0.77
    Activations Density 0.011%

    No Known Activations