INDEX

Explanations

intensifiers that emphasize the quality or extent of something

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

intensifiers like very

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

</tfoot>

-0.64

SequentialGroup

-0.57

 CURIAM

-0.57

ValueStyle

-0.57

GraphicsUnit

-0.53

EndContext

-0.51

ſchaft

-0.50

writeFieldEnd

-0.50

UrlResolution

-0.49

 témoig

-0.48

POSITIVE LOGITS

 very

1.13

 Very

0.96

 VERY

0.95

Very

0.92

very

0.91

 sehr

0.82

 bardzo

0.82

 очень

0.80

 extremely

0.79

 zeer

0.79

Activations Density 0.024%

intensifiers that emphasize the quality or extent of something

intensifiers like very

No Comments

No Known Activations