INDEX

Explanations

numeric data and measures, particularly in a scientific context

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

1:x ratios

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

ſchen

-0.52

waiter

-0.51

criptors

-0.51

vė

-0.51

braucher

-0.50

bootstrapcdn

-0.50

 programmer

-0.49

tamaris

-0.48

imageshack

-0.48

cknow

-0.48

POSITIVE LOGITS

 Ratio

0.58

 ratio

0.57

ratio

0.48

Ratio

0.45

 ratios

0.43

 Ratios

0.42

ContentAsync

0.42

RATIO

0.39

 RATIO

0.38

WithIOException

0.36

Activations Density 0.066%

numeric data and measures, particularly in a scientific context

1:x ratios

No Comments

No Known Activations