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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 16274
    Prev
    Next
    INDEX
    Explanations

    the letter 'r' with an emphasis on the numbers 9 and 10

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'r'

    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
     EntityItem
    -0.79
    £ı
    -0.73
     CPR
    -0.68
     Contra
    -0.65
     reusable
    -0.65
    æĸ¹
    -0.65
    Ĥ¬
    -0.62
     removable
    -0.62
     statically
    -0.62
     Corpus
    -0.62
    POSITIVE LOGITS
    abbit
    1.22
    acing
    1.21
    agh
    1.15
    agnar
    1.13
    ach
    1.10
    ifts
    1.10
    ussia
    1.10
    angers
    1.07
    outine
    1.05
    anger
    1.04
    Activations Density 0.044%

    No Known Activations