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. 10-RES-JB
    6. 18430
    Prev
    Next
    INDEX
    Explanations

    cryptic sequences of characters ('Ċ') along with the word "Mercury"

    oai_token-act-pair · gpt-3.5-turbo

    instances of emphasis or intensity within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     proport
    -0.88
     exha
    -0.76
     occas
    -0.76
     communications
    -0.74
     undermin
    -0.74
     endeav
    -0.72
     neighb
    -0.70
     duty
    -0.70
    hement
    -0.69
     inactive
    -0.68
    POSITIVE LOGITS
    ³³³³³³³³
    1.19
    ³³³³³³³³³³³³³³³³
    1.19
    Posted
    1.18
    ³³³³
    1.17
    ³³³
    1.13
    posted
    1.04
    SPONSORED
    1.04
    Anyway
    0.97
    AMY
    0.96
    ³³
    0.96
    Activations Density 0.496%

    No Known Activations