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. 0-RES-JB
    6. 5253
    Prev
    Next
    INDEX
    Explanations

    words depicting a strong emphasis or focus on something

    oai_token-act-pair · gpt-3.5-turbo

    words that express emphasis or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fa
    -0.58
     Typhoon
    -0.57
     Disp
    -0.55
     Freedom
    -0.55
    Dev
    -0.54
     Net
    -0.53
     Starter
    -0.52
     Add
    -0.52
     veins
    -0.52
     Inf
    -0.51
    POSITIVE LOGITS
    arily
    5.20
    aries
    1.95
    ary
    1.83
    ARY
    1.81
    istically
    1.47
    ally
    1.45
    ously
    1.41
    ially
    1.36
    itatively
    1.33
    atically
    1.29
    Activations Density 0.008%

    No Known Activations