INDEX

Explanations

questions starting with "what" and related phrases

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

Begins questions

np_acts-logits-general · gemini-2.0-flash

asking what

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

wapV

-0.59

crollView

-0.50

Bibliography

-0.49

 Liberties

-0.48

 кӀ

-0.48

WSGI

-0.48

 onOptions

-0.46

Mue

-0.45

InstanceState

-0.45

ThroughAttribute

-0.45

POSITIVE LOGITS

 Baillargeon

0.64

AndEndTag

0.63

BeginContext

0.55

 تضيفلها

0.55

期刊论文

0.54

 насељу

0.54

AsUp

0.52

 nakalista

0.52

 Catawiki

0.51

 kaarangay

0.50

Activations Density 0.081%

questions starting with "what" and related phrases

Begins questions

asking what

No Comments

No Known Activations