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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 2220
    Prev
    Next
    INDEX
    Explanations

    mentions of violent events, especially involving women and children

    oai_token-act-pair · gpt-3.5-turbo

    references to violence and its impact on women and children

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.78
     Hamilton
    -0.78
     Gemini
    -0.77
    ooth
    -0.77
    Scot
    -0.77
     Disclosure
    -0.76
     Madison
    -0.75
     Salary
    -0.74
    Madison
    -0.74
     Ames
    -0.74
    POSITIVE LOGITS
     evacuated
    1.02
     evacuate
    0.88
    zbollah
    0.88
     militants
    0.86
     looted
    0.85
     bombed
    0.84
     detonated
    0.83
     villagers
    0.82
     shelling
    0.82
    merga
    0.82
    Activations Density 0.488%

    No Known Activations