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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20703
    Prev
    Next
    INDEX
    Explanations

    social media terminology and user engagement prompts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Like" in relation to engagement or social media interactions

    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
    Ö¼
    -0.64
    inas
    -0.61
    ENE
    -0.61
    quarter
    -0.60
    cill
    -0.60
    士
    -0.58
     extracted
    -0.58
     intermedi
    -0.54
    overy
    -0.54
    ape
    -0.54
    POSITIVE LOGITS
    lihood
    1.80
     minded
    1.15
    minded
    1.15
    liness
    1.04
    liest
    1.04
     Loading
    0.94
    lier
    0.86
     Us
    0.80
     Clockwork
    0.80
    ability
    0.78
    Activations Density 0.043%

    No Known Activations