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. 2-RES-JB
    6. 2496
    Prev
    Next
    INDEX
    Explanations

    mention the word "Nec" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of necessity or essentiality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.82
     Feld
    -0.79
    nings
    -0.76
     Wink
    -0.68
     Beckham
    -0.67
    à¹
    -0.64
     Miranda
    -0.64
    gered
    -0.64
     Mata
    -0.62
     Glover
    -0.62
    POSITIVE LOGITS
    romancer
    1.19
    ropolis
    1.08
    hemy
    0.88
    urg
    0.87
    ertain
    0.85
     Nec
    0.84
    rast
    0.82
    ulhu
    0.80
    ensibly
    0.79
    aleb
    0.79
    Activations Density 0.011%

    No Known Activations