INDEX

Explanations

instances of administrative or bureaucratic references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AndEndTag

-0.67

Espèce

-0.65

 समीक्षाएं

-0.65

itek

-0.62

+#+#

-0.61

StoryboardSegue

-0.61

ècie

-0.59

 degenerate

-0.58

 kasarigan

-0.58

ViewFeatures

-0.57

POSITIVE LOGITS

Insee

0.60

Personensuche

0.56

claimer

0.55

 fermés

0.54

脚注の使い方

0.54

Facades

0.53

postmedia

0.53

rodow

0.53

medriver

0.52

entendre

0.52

Activations Density 0.122%

instances of administrative or bureaucratic references

No Comments

No Known Activations