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. 2-RES-JB
    6. 9570
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the impact or consequences of something

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to the consequences or impacts of various factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CFL
    -0.70
    bor
    -0.69
    space
    -0.64
     Gall
    -0.64
    HEAD
    -0.64
    mint
    -0.63
    ths
    -0.63
    mbuds
    -0.62
    cin
    -0.62
    spect
    -0.62
    POSITIVE LOGITS
    effects
    1.29
    iveness
    1.12
     effects
    1.10
    Effects
    0.94
     confir
    0.89
    ively
    0.87
     effect
    0.87
     Effects
    0.86
     consequences
    0.84
    uel
    0.84
    Activations Density 0.024%

    No Known Activations