INDEX

Explanations

statements emphasizing the importance or significance of a fact.

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

"fact" and its usage

np_acts-logits-general · gemini-2.0-flash

the fact that

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

RenderAtEndOf

-0.87

ագրություններ

-0.87

 initComponents

-0.82

sterious

-0.80

 समीक्षक

-0.78

yntaxException

-0.78

awaiter

-0.76

 onResponse

-0.73

ρους

-0.72

 aceptas

-0.72

POSITIVE LOGITS

 fact

1.14

 Fact

0.89

fact

0.87

 FACT

0.84

 facts

0.77

 Facts

0.77

Fact

0.72

FACT

0.71

 FACTS

0.69

facts

0.67

Activations Density 0.070%

statements emphasizing the importance or significance of a fact.

"fact" and its usage

the fact that

No Comments

No Known Activations