INDEX

Explanations

phrases that indicate consensus or agreement

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 propOrder

-0.83

 Exactos

-0.78

TagMode

-0.72

 initComponents

-0.70

 Meksiku

-0.68

/**

-0.66

 ExecuteAsync

-0.63

 povezave

-0.62

 pageContext

-0.60



-0.59

POSITIVE LOGITS

bollah

0.65

riwal

0.64

RenderAtEndOf

0.57

 biografias

0.55

SharedCtor

0.55

resizingMask

0.54

MatButtonModule

0.53

__*/

0.50

 doInBackground

0.49

ollectionView

0.49

Activations Density 0.018%

phrases that indicate consensus or agreement

No Comments

No Known Activations