INDEX

Explanations

expressions of magnitude or intensity related to concepts and experiences

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

Adjective followed by "an"

np_acts-logits-general · gemini-2.0-flash

describing 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 @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Enough

-1.04

 enough

-0.99

 sufficiently

-0.96

enough

-0.96

 تضيفلها

-0.94

Enough

-0.92

 suficientes

-0.90

 ENOUGH

-0.89

 suficiente

-0.89

 suffisamment

-0.88

POSITIVE LOGITS

0.59

 looking

0.59

 sounding

0.54

 actually

0.54

0.53

looking

0.52

getItemId

0.51

of

0.47

sworth

0.47

 feeling

0.45

Activations Density 0.305%

expressions of magnitude or intensity related to concepts and experiences

Adjective followed by "an"

describing degree or extent

No Comments

No Known Activations