INDEX

Explanations

phrases indicating significance or magnitude in context

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

Preceding words indicating large quantity or ability

np_acts-logits-general · gemini-2.0-flash

quantifying degree or extent

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

naco

-0.53

ung

-0.52

安い

-0.50

occupe

-0.50

DOCTYPE

-0.49

Geplaatst

-0.48

trand

-0.48

Pricing

-0.48

 Cheaper

-0.48

occuper

-0.47

POSITIVE LOGITS

 amount

0.82

NUMX

0.78

IBarButtonItem

0.76

 extent

0.75

 pleaſure

0.74

 myſelf

0.73

 amounts

0.72

 ſever

0.72

sizeCache

0.71

 Extent

0.69

Activations Density 0.472%

phrases indicating significance or magnitude in context

Preceding words indicating large quantity or ability

quantifying degree or extent

No Comments

No Known Activations