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. 8-RES-JB
    6. 18131
    Prev
    Next
    INDEX
    Explanations

    references to intensity or high levels of something

    oai_token-act-pair · gpt-3.5-turbo

    the word "Int" and its variations or related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gleaming
    -0.76
    wagen
    -0.70
    hyde
    -0.68
     palms
    -0.68
    ¶ħ
    -0.67
    pees
    -0.65
    baum
    -0.62
    awaru
    -0.61
    pee
    -0.61
     lions
    -0.60
    POSITIVE LOGITS
    ensive
    1.28
    ention
    1.28
    ellect
    1.27
    ensity
    1.19
    ellig
    1.14
    estinal
    1.10
    ENTION
    1.08
    ensions
    1.06
    angible
    1.05
    rast
    1.04
    Activations Density 0.028%

    No Known Activations