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. 7-RES-JB
    6. 17014
    Prev
    Next
    INDEX
    Explanations

    terms related to different forms of abuse, such as physical, emotional, and financial abuse

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "abuse" and its varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cil
    -0.85
    travel
    -0.78
    izen
    -0.73
    pard
    -0.73
    ailed
    -0.68
    pai
    -0.67
    views
    -0.66
    vision
    -0.66
    cise
    -0.65
    printed
    -0.64
    POSITIVE LOGITS
    abuse
    0.92
     abusing
    0.84
     abuse
    0.80
     perpetrated
    0.80
     inflicted
    0.77
     abused
    0.74
     victims
    0.74
     tactics
    0.73
     abuses
    0.72
     abusers
    0.72
    Activations Density 0.024%

    No Known Activations