INDEX

Explanations

references to time intervals and durations

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

phrases indicating something happened within a brief timespan, such as "within a short period," "in a couple of nights," or "in days."

oai_token-act-pair · claude-3-7-sonnet-20250219 Triggered by @neilrathi

phrases describing rapid accomplishment or development occurring within a brief timeframe.

oai_token-act-pair · claude-4-5-haiku Triggered by @emiglarou

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 occafion

-0.43

やっと

-0.42

occasion

-0.34

年以上

-0.34

DockStyle

-0.33

 occaf

-0.33

一直

-0.32

큼

-0.32

until

-0.32

hasta

-0.31

POSITIVE LOGITS

 less

1.16

わずか

1.16

短短

1.13

 short

1.07

 Less

1.02

不到

1.02

 kısa

0.99

 shortest

0.98

Less

0.98

 kurzer

0.97

Activations Density 0.357%

references to time intervals and durations

phrases indicating something happened within a brief timespan, such as "within a short period," "in a couple of nights," or "in days."

phrases describing rapid accomplishment or development occurring within a brief timeframe.

No Comments

No Known Activations

references to time intervals and durations

phrases indicating something happened within a brief timespan, such as "within a short period," "in a couple of nights," or "in days."

phrases describing rapid accomplishment or development occurring within a brief timeframe.

No Comments

No Known Activations