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. 6590
    Prev
    Next
    INDEX
    Explanations

    names or references related to the name "Os"

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the term "Os," likely indicating a specific location or subject

    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
    ingly
    -0.78
    ãĥ¼ãĥĨãĤ£
    -0.77
     Caribbean
    -0.74
    heid
    -0.72
    ãģ®éŃĶ
    -0.71
    ************
    -0.69
    åij
    -0.68
    ances
    -0.67
    âķIJâķIJ
    -0.65
     SEAL
    -0.65
    POSITIVE LOGITS
    entle
    0.93
    odes
    0.90
    mia
    0.90
    acco
    0.88
    ocom
    0.87
    aret
    0.85
    ucha
    0.85
    atom
    0.85
    rien
    0.84
    pher
    0.84
    Activations Density 0.024%

    No Known Activations