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. 1-RES-JB
    6. 8454
    Prev
    Next
    INDEX
    Explanations

    references to increasing or growing pressure, tension, or criticism

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to increasing pressure or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesota
    -0.82
    clamation
    -0.79
    anguages
    -0.76
    asm
    -0.72
    go
    -0.71
    uv
    -0.71
    ander
    -0.67
    razil
    -0.67
    okia
    -0.67
    houn
    -0.66
    POSITIVE LOGITS
     mounting
    1.33
     mounts
    1.16
    mount
    1.12
     mount
    1.05
     mounted
    1.04
     srfAttach
    0.95
    mounted
    0.91
     unbeliev
    0.82
    Mount
    0.82
    ounter
    0.75
    Activations Density 0.007%

    No Known Activations