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. 1-RES-JB
    6. 9865
    Prev
    Next
    INDEX
    Explanations

    words related to alternatives or different options

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "alternate" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.80
    manship
    -0.66
    mers
    -0.66
    ocene
    -0.66
    faced
    -0.66
     majesty
    -0.66
    stakes
    -0.65
     endif
    -0.64
    kens
    -0.63
    delay
    -0.62
    POSITIVE LOGITS
    ative
    0.89
     fortun
    0.83
    altern
    0.82
    ocate
    0.82
    ational
    0.81
    dayName
    0.80
    atives
    0.75
    aily
    0.75
     Scand
    0.75
    itely
    0.74
    Activations Density 0.012%

    No Known Activations