Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 6616
    Prev
    Next
    INDEX
    Explanations

    obscured words containing the letters "ob" in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    references to "obituaries" or related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActiveUnfocused
    -1.01
    EngineDebug
    -0.99
    agne
    -0.83
    anwhile
    -0.80
     Prosper
    -0.75
     Carlson
    -0.73
     gas
    -0.73
    terday
    -0.72
     Michaels
    -0.70
     Idle
    -0.68
    POSITIVE LOGITS
    lique
    1.53
    livion
    1.30
    eyed
    1.15
    structed
    1.11
    nox
    1.07
    sole
    1.04
    amacare
    1.03
    olescent
    1.03
    tains
    1.03
    ject
    1.01
    Activations Density 0.013%

    No Known Activations