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. 10-RES-JB
    6. 15221
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or actions coming to a conclusion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ended" or variations of it, indicating conclusions or closures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Parables
    -0.66
    hee
    -0.60
    leted
    -0.60
    iard
    -0.59
     broom
    -0.56
    pillar
    -0.56
    onne
    -0.55
    average
    -0.55
    esome
    -0.54
    è¦ļéĨĴ
    -0.54
    POSITIVE LOGITS
     abruptly
    1.27
     prematurely
    1.18
     tragically
    1.08
     peacefully
    1.02
    angering
    1.01
    angers
    0.98
    eared
    0.93
    owment
    0.85
     badly
    0.85
    orses
    0.85
    Activations Density 0.039%

    No Known Activations