INDEX

Explanations

transitions or markers indicating sections or segments in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

 ſtate

-0.97

 myſelf

-0.94

 ſche

-0.92

ſelf

-0.91

 pleaſure

-0.90

 ſever

-0.89

 purpoſe

-0.88

 ſeveral

-0.87

 ftate

-0.87

uſ

-0.85

POSITIVE LOGITS

Finally

0.55

Lastly

0.53

↵↵

0.50

↵

0.50

 Finally

0.48

Alongside

0.45

Aside

0.44

Despite

0.42

 Lastly

0.42

 наконец

0.40

Activations Density 0.084%

transitions or markers indicating sections or segments in a text

No Comments

No Known Activations