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. 5460
    Prev
    Next
    INDEX
    Explanations

    phrases related to suppression or control of emotions

    oai_token-act-pair · gpt-3.5-turbo

    words related to depression and emotional distress

    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
     otherwise
    -0.78
     prepaid
    -0.69
     telev
    -0.64
     consum
    -0.62
     astronomical
    -0.61
     ordinarily
    -0.60
     dwar
    -0.59
    ç«
    -0.58
     attract
    -0.58
     mint
    -0.58
    POSITIVE LOGITS
    ression
    4.33
    ressed
    2.22
    ressor
    2.08
    ress
    2.07
    ressing
    2.04
    resses
    1.78
    ressive
    1.62
    artment
    1.07
    ansion
    1.06
    ilation
    1.03
    Activations Density 0.009%

    No Known Activations