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. 10911
    Prev
    Next
    INDEX
    Explanations

    abbreviations starting with the letter 'V'

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or brand represented by 'V'

    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
    ģĸ
    -0.70
    ¯¯
    -0.65
    ãĤ´ãĥ³
    -0.63
     deduction
    -0.62
    ¯¯¯¯
    -0.61
     unrestricted
    -0.60
     takedown
    -0.59
     AAA
    -0.59
     writ
    -0.59
    names
    -0.58
    POSITIVE LOGITS
    oodoo
    1.41
    ulture
    1.34
    arsity
    1.32
    odka
    1.28
    isions
    1.26
    antage
    1.26
    icious
    1.22
    ampires
    1.20
    ulnerability
    1.20
    ISION
    1.20
    Activations Density 0.028%

    No Known Activations