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. 9-RES-JB
    6. 12879
    Prev
    Next
    INDEX
    Explanations

    phrases related to defending a position or a person

    oai_token-act-pair · gpt-3.5-turbo

    words related to defense or defending

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FORE
    -0.70
    way
    -0.66
     bleed
    -0.63
    hook
    -0.63
    ISA
    -0.62
    =~=~
    -0.62
    INFO
    -0.61
    ombies
    -0.60
    Machine
    -0.59
    foot
    -0.59
    POSITIVE LOGITS
     against
    1.26
     Against
    1.12
    against
    1.02
     indef
    0.87
     vigorously
    0.87
    iveness
    0.85
    atively
    0.85
    ously
    0.82
    ively
    0.80
     AGA
    0.76
    Activations Density 0.044%

    No Known Activations