INDEX

Explanations

references to fish or related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Bly

-1.03

клопе

-1.03

 rospy

-1.01

 maxSize

-0.98

 itſelf

-0.92

 poffible

-0.90

 myſelf

-0.87

 leaſt

-0.86

maxSize

-0.84

 greateſt

-0.84

POSITIVE LOGITS

 fish

1.82

 Fish

1.73

 FISH

1.63

Fish

1.52

fish

1.44

 fishes

1.41

FISH

1.35

 Fisch

1.22

 Fishes

1.14

 pescado

1.11

Activations Density 0.074%

references to fish or related topics

No Comments

No Known Activations