INDEX

Explanations

variations of the word "pose" and related concepts regarding condition or state

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

 Spro

-0.54

 doğ

-0.53

 émer

-0.52

 dép

-0.49

 Niedersch

-0.49

 tantum

-0.48

 UserProfile

-0.47

 orari

-0.47

 morta

-0.47

ingan

-0.46

POSITIVE LOGITS

 empowering

0.78

rifying

0.78

 transformative

0.77

 disambiguazione

0.75

sizeCache

0.74

 disruptive

0.74

makeConstraints

0.73

ariest

0.73

setVerticalGroup

0.73

LLocation

0.71

Activations Density 0.460%

variations of the word "pose" and related concepts regarding condition or state

No Comments

No Known Activations