INDEX

Explanations

references to the word "what" in various contexts

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

"what"

np_acts-logits-general · gemini-2.0-flash

what followed by pronouns or verbs

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Verge

-0.56

☆☆

-0.55

AMC

-0.54

mez

-0.54

 مشين

-0.52

str

-0.52

liez

-0.52

erl

-0.50

oucí

-0.50

POSITIVE LOGITS

 WHAT

1.04

WHAT

0.98

 what

0.98

 What

0.95

what

0.91

What

0.88

ArgsConstructor

0.79

 happened

0.78

 happens

0.77

 <=",

0.74

Activations Density 0.127%

references to the word "what" in various contexts

"what"

what followed by pronouns or verbs

No Comments

No Known Activations