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. 15904
    Prev
    Next
    INDEX
    Explanations

    situations where an action is taken or a decision is made regarding a person's rights or movement

    oai_token-act-pair · gpt-3.5-turbo

    instances where individuals are subjected to various legal or societal conditions affecting their rights and responsibilities

    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
     Traps
    -0.77
    soDeliveryDate
    -0.76
     corridors
    -0.74
     pipelines
    -0.73
     divisions
    -0.69
     Customers
    -0.69
     Lines
    -0.69
    Newsletter
    -0.68
     closures
    -0.67
    IVERS
    -0.67
    POSITIVE LOGITS
     whom
    0.81
     voluntarily
    0.75
     himself
    0.74
     immersed
    0.72
     exercising
    0.70
     passively
    0.68
     invol
    0.66
     veto
    0.63
    elf
    0.63
     mentally
    0.63
    Activations Density 0.469%

    No Known Activations