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. 3-RES-JB
    6. 21651
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the letter "T" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "T" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.81
     cannabin
    -0.76
     actionGroup
    -0.75
    EStream
    -0.74
     ment
    -0.70
    ħĭ
    -0.67
     destro
    -0.66
    76561
    -0.62
     gorilla
    -0.62
     diapers
    -0.62
    POSITIVE LOGITS
    ARGET
    1.24
    ribute
    1.19
    ributes
    1.13
    olerance
    1.12
    ractor
    1.10
    ract
    1.07
    ruck
    1.05
    agged
    1.05
    unes
    1.04
    uple
    1.04
    Activations Density 0.082%

    No Known Activations