INDEX

Explanations

phrases indicating familiarity or habitual actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 الحره

-0.64

liato

-0.60

vő

-0.56

 Trouver

-0.56

 moratorium

-0.54

ranton

-0.53

hasNext

-0.53

CAPTION

-0.52

SharedDtor

-0.52

feira

-0.51

POSITIVE LOGITS

 accustomed

1.19

 acostumb

1.01

 привы

0.90

慣

0.86

habitude

0.85

 habitu

0.85

 acost

0.84

 alış

0.82

慣れて

0.82

 familiarity

0.78

Activations Density 0.227%

phrases indicating familiarity or habitual actions

No Comments

No Known Activations