INDEX

Explanations

numerical values and the word "we"

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

AnimationsModule

-0.64

sidemargin

-0.61

 հղումներ

-0.56

ГЛА

-0.54

ponses

-0.54



-0.52

Rüyada

-0.51

Clik

-0.51

Vidite

-0.50

 JSTOR

-0.50

POSITIVE LOGITS

 kasarigan

0.65

VolleyError

0.59

Erreferentziak

0.56

 صوتيه

0.55

يميديا

0.52

eafter

0.52

exitRule

0.51

uidado

0.51

 '\\;'

0.49

 jelasnya

0.49

Activations Density 0.222%

numerical values and the word "we"

No Comments

No Known Activations