Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-RES-JB
    6. 19157
    Prev
    Next
    INDEX
    Explanations

    the word "same."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of sameness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ases
    -0.73
    *=-
    -0.68
    rection
    -0.68
    orsi
    -0.66
    rosso
    -0.65
    åĪ
    -0.65
    bane
    -0.65
    gets
    -0.63
    omics
    -0.63
    icism
    -0.62
    POSITIVE LOGITS
     thing
    0.93
     exact
    0.88
     amount
    0.72
     ol
    0.71
     kind
    0.70
     principle
    0.70
     sized
    0.68
    yll
    0.68
     old
    0.67
     vein
    0.66
    Activations Density 0.033%

    No Known Activations