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. 3-RES-JB
    6. 7363
    Prev
    Next
    INDEX
    Explanations

    words related to a specific term "ult"

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to cultural or artistic phenomena, specifically those using the prefix 'ult'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĸ¬
    -0.75
    ETS
    -0.68
     Blaz
    -0.68
    ãģ®éŃĶ
    -0.68
    女
    -0.66
    ¶ħ
    -0.66
    CHR
    -0.66
    STON
    -0.66
    strings
    -0.66
    forth
    -0.65
    POSITIVE LOGITS
    iple
    1.16
    raviolet
    1.15
    imately
    1.14
    imates
    1.04
    icult
    0.94
    urally
    0.93
    icide
    0.92
    icultural
    0.92
    amines
    0.91
    ancy
    0.90
    Activations Density 0.009%

    No Known Activations