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. 8-RES-JB
    6. 9536
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "Its" followed by a positive or negative statement

    oai_token-act-pair · gpt-3.5-turbo

    the word "its" and its variations, indicating descriptions or references to possession or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    --+
    -0.74
    VS
    -0.68
     Thib
    -0.67
    iatus
    -0.65
    ï
    -0.65
    ievers
    -0.64
     Obj
    -0.64
    GB
    -0.63
    ":[
    -0.62
    imedia
    -0.61
    POSITIVE LOGITS
    ELF
    1.12
     gonna
    0.93
     predecessor
    0.90
     worth
    0.88
     been
    0.87
     supposed
    0.85
     own
    0.85
    elf
    0.83
    omorph
    0.82
    been
    0.82
    Activations Density 0.097%

    No Known Activations