INDEX

Explanations

statements related to authority and governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 namin

-0.56

StructEnd

-0.54

TextWatcher

-0.53

httphttps

-0.53

waitUntil

-0.51

inige

-0.50

المصدر

-0.50

 useCallback

-0.49

queryInterface

-0.49

ModelAdmin

-0.49

POSITIVE LOGITS

 Apart

0.75

 apart

0.74

Apart

0.72

apart

0.66

 Incidentally

0.61

Needless

0.59

 indeed

0.59

withstanding

0.58

 notwithstanding

0.57

 Recall

0.57

Activations Density 0.038%

statements related to authority and governance

No Comments

No Known Activations