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. 15691
    Prev
    Next
    INDEX
    Explanations

    chemical terms or references

    oai_token-act-pair · gpt-3.5-turbo

    terms related to chemistry and chemotherapy

    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
    lihood
    -0.86
     Eston
    -0.82
     Vikings
    -0.79
     Icelandic
    -0.76
     Uzbek
    -0.72
     Bridgewater
    -0.71
     Isles
    -0.68
    FORE
    -0.68
     Timberwolves
    -0.67
     Rough
    -0.67
    POSITIVE LOGITS
    icals
    1.22
    chem
    1.04
    icians
    1.01
    istry
    1.00
    otherapy
    0.99
    istries
    0.98
    uria
    0.96
     chem
    0.94
    ician
    0.91
    netic
    0.88
    Activations Density 0.012%

    No Known Activations