INDEX

Explanations

references to numerical values and their relationships in scientific contexts

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

Comes after "large", "high", or "low"

np_acts-logits-general · gemini-2.0-flash

large coupling or high frequency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

########.

-0.59

multicolumn

-0.50

tė

-0.49

pagestyle

-0.49

 morir

-0.49

SBATCH

-0.48

Čo

-0.47

 équilibr

-0.47

 fér

-0.47

UrlResolution

-0.47

POSITIVE LOGITS

 distance

0.71

 propOrder

0.64

omock

0.61

 Lokales

0.59

MessageState

0.57

 quen

0.56

 absc

0.53

distance

0.53

 argument

0.52

ESSOR

0.52

Activations Density 1.611%

references to numerical values and their relationships in scientific contexts

Comes after "large", "high", or "low"

large coupling or high frequency

No Comments

No Known Activations