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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 23623
    Prev
    Next
    INDEX
    Explanations

    word sequences related to harassment, discrimination, abuse, violence and assault

    oai_token-act-pair · gpt-3.5-turbo

    references to harassment, violence, and related abuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liam
    -0.78
     Bucket
    -0.77
    DragonMagazine
    -0.74
     Tycoon
    -0.74
    Legendary
    -0.71
    ernels
    -0.71
     Compact
    -0.71
    */(
    -0.69
    natureconservancy
    -0.68
    phalt
    -0.67
    POSITIVE LOGITS
     intimidation
    1.63
     harassment
    1.52
     retaliation
    1.49
     bullying
    1.43
     discrimination
    1.42
     coercion
    1.36
     harassing
    1.34
     unwelcome
    1.31
     derogatory
    1.31
     threats
    1.27
    Activations Density 0.322%

    No Known Activations