INDEX

Explanations

mentions of flags, particularly national and state flags

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 للمعارف

-0.62

 يتيمه

-0.57

 שוליים

-0.53

iastes

-0.51

vegli

-0.50

FormTagHelper

-0.50

ագրություններ

-0.50

UnitTesting

-0.50

wpdb

-0.49

 виправивши

-0.49

POSITIVE LOGITS

 flag

1.81

 flags

1.60

 Flag

1.57

flag

1.53

Flag

1.44

 Flags

1.35

 drapeau

1.29

 FLAG

1.26

Flags

1.24

flags

1.21

Activations Density 0.256%

mentions of flags, particularly national and state flags

No Comments

No Known Activations