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. 4-RES-JB
    6. 21206
    Prev
    Next
    INDEX
    Explanations

    terms related to negative or harmful actions or situations, such as bullying and fear-mongering

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles related to negative actions or behaviors

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

    No Comments

    Negative Logits
    omet
    -0.85
    Ô
    -0.74
    OPE
    -0.64
    rez
    -0.64
     Roll
    -0.62
    ivot
    -0.60
    Pos
    -0.59
    spot
    -0.58
    mpeg
    -0.57
     Baz
    -0.57
    POSITIVE LOGITS
    tons
    0.87
     spree
    0.86
     tactics
    0.86
     techniques
    0.78
    redients
    0.76
     antics
    0.75
     rituals
    0.75
    aukee
    0.74
     prowess
    0.73
    HAM
    0.73
    Activations Density 0.098%

    No Known Activations