INDEX

Explanations

references to fish in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

клопе

-1.07

 rospy

-1.03

Bly

-1.02

 maxSize

-1.01

ContentAlignment

-0.98

 itſelf

-0.97

 poffible

-0.94

 myſelf

-0.92

 Confu

-0.87

 leaſt

-0.87

POSITIVE LOGITS

 fish

1.92

 Fish

1.80

 FISH

1.69

Fish

1.56

fish

1.50

 fishes

1.44

FISH

1.41

 Fisch

1.34

 Fisher

1.23

 Fishes

1.22

Activations Density 0.069%

references to fish in various contexts

No Comments

No Known Activations