INDEX

Explanations

elements related to communication and questioning in discussions

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

 calendriers

-0.60

Vidite

-0.56

 Prow

-0.55

 astore

-0.52

ürzen

-0.52

quième

-0.52

 Branch

-0.51

érial

-0.51

PoolSize

-0.50

orten

-0.49

POSITIVE LOGITS

contentLoaded

0.60

 المعيارى

0.55

principalColumn

0.53

 Chwiliwch

0.52

idenav

0.52

 Савез

0.52

UseVisualStyle

0.51

RTDA

0.50

EnumMember

0.50

AddTagHelper

0.50

Activations Density 1.030%

elements related to communication and questioning in discussions

No Comments

No Known Activations