INDEX

Explanations

verbs that indicate action or occurrence related to processes or results

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

 themselves

-0.72

HtmlAttribute

-0.65

copg

-0.61

MLLoader

-0.59

are

-0.59

 "..\..\..\

-0.58

 Meksiku

-0.57

DataPropertyName

-0.56

φι

-0.56

 شوند

-0.56

POSITIVE LOGITS

 CreateTagHelper

0.55

expandindo

0.54

seems

0.49

 telle

0.48

wasan

0.46

sieht

0.46

zysta

0.46

 Umbra

0.45

 pits

0.45

 menak

0.44

Activations Density 0.468%

verbs that indicate action or occurrence related to processes or results

No Comments

No Known Activations