INDEX

Explanations

evidence and assertions related to proving or demonstrating a point

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

"prove" or variations of it

np_acts-logits-general · gemini-2.0-flash

proving factual claims

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للاسماء

-0.60

Datuak

-0.58

OCCURRED

-0.57

icol

-0.54

NetworkInfo

-0.51

setdefault

-0.48

Eto

-0.46

 portu

-0.46

 préférences

-0.45

ReusableCell

-0.45

POSITIVE LOGITS

 Prove

1.11

 prove

1.05

 proved

0.93

Prove

0.93

 proves

0.92

 proving

0.88

prove

0.86

 conclusively

0.84

proved

0.78

 XCTest

0.78

Activations Density 0.116%

evidence and assertions related to proving or demonstrating a point

"prove" or variations of it

proving factual claims

No Comments

No Known Activations