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. 16924
    Prev
    Next
    INDEX
    Explanations

    words with the sequence "ien" in them, with a higher preference for those with "ien" followed by non-alphabetic characters

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the substring "ien" in various contexts

    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
    è¦ļéĨĴ
    -1.08
    ramid
    -0.73
    mable
    -0.66
    Discussion
    -0.65
     spaced
    -0.62
     mids
    -0.61
    hematic
    -0.60
     variance
    -0.60
    tub
    -0.59
     stocking
    -0.59
    POSITIVE LOGITS
    emy
    1.05
    ien
    0.97
    vironment
    0.94
    cia
    0.94
    icidal
    0.92
    emort
    0.88
    ews
    0.86
    emies
    0.86
    ienne
    0.81
    icides
    0.80
    Activations Density 0.007%

    No Known Activations