INDEX

Explanations

terms associated with assumption or supposition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

joueurs

-0.49

Datuak

-0.48

 allegedly

-0.48

on

-0.48

gdx

-0.45

 reportedly

-0.45

 ensured

-0.44

-0.43

 исследований

-0.42

 став

-0.42

POSITIVE LOGITS

Personensuche

1.00

timate

0.85

MIDDLEWARE

0.84

 ProtoMessage

0.83

IMATE

0.81

الإنجليزية

0.79

 Meksiku

0.79

ableness

0.77

✨:

0.76

 виправивши

0.76

Activations Density 0.233%

terms associated with assumption or supposition

No Comments

No Known Activations