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. 4-RES-JB
    6. 22160
    Prev
    Next
    INDEX
    Explanations

    phrases related to making up for something or compensating for a loss

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate making up for something or compensating

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

    No Comments

    Negative Logits
    ensen
    -0.76
    cles
    -0.73
    grand
    -0.70
    CLE
    -0.67
     compares
    -0.66
     threw
    -0.65
    caps
    -0.64
    elson
    -0.64
     prefers
    -0.64
     nicknamed
    -0.63
    POSITIVE LOGITS
     instance
    0.89
     example
    0.83
    gotten
    0.79
     eternity
    0.77
     grabs
    0.73
    going
    0.73
     oneself
    0.73
     hire
    0.73
     yourselves
    0.71
    riage
    0.71
    Activations Density 0.099%

    No Known Activations