INDEX

Explanations

instances of articles and determiners 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 @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 myſelf

-1.69

 itſelf

-1.58

parsedMessage

-1.56

 pleaſure

-1.42

 faſt

-1.40

IsMutable

-1.39

 cauſe

-1.37

 purpoſe

-1.36

 becauſe

-1.35

ſelf

-1.33

POSITIVE LOGITS

1.21

↵

1.20

1.19

1.17

↵↵

1.09

1.07

1.03

’

0.99

0.96

Activations Density 0.562%

instances of articles and determiners in various contexts

No Comments

No Known Activations