INDEX

Explanations

expressions that denote excessive quantities or qualities

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

"Too" followed by an adjective

np_acts-logits-general · gemini-2.0-flash

Too followed by adjective/adverb

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

oredCriteria

-0.73

roves

-0.65

 rost

-0.65

{})

-0.59

.)

-0.56

-0.55

 orienta

-0.54

lans

-0.53

もので

-0.53

celot

-0.52

POSITIVE LOGITS

TOO

0.87

Too

0.86

TOO

0.84

 estekak

0.81

too

0.81

Too

0.80

 much

0.80

too

0.79

troppo

0.69

 TOOL

0.65

Activations Density 0.044%

expressions that denote excessive quantities or qualities

"Too" followed by an adjective

Too followed by adjective/adverb

No Comments

No Known Activations