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. 11-RES-JB
    6. 4458
    Prev
    Next
    INDEX
    Explanations

    instances of the word "first" in a text

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "first" or initial occurrences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    md
    -0.76
    ingen
    -0.75
    roit
    -0.72
    bu
    -0.71
    bsp
    -0.69
    hend
    -0.67
    fu
    -0.67
    ITH
    -0.67
    bia
    -0.66
    anism
    -0.66
    POSITIVE LOGITS
     thing
    1.31
     hurdle
    0.98
     step
    0.97
     question
    0.96
     clue
    0.95
     reason
    0.92
     indication
    0.91
     caveat
    0.89
     installment
    0.86
     lesson
    0.86
    Activations Density 0.098%

    No Known Activations