INDEX

Explanations

usage of the indefinite article "a" in diverse contexts

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

"a" followed by a noun

np_acts-logits-general · gemini-2.0-flash

a followed by a word

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

<bos>

-0.80

AddHtmlAttribute

-0.58

FunctionFlags

-0.56

médiaire

-0.53

fjspx

-0.49

 szint

-0.49

 tutt

-0.48

 enfance

-0.48

sizeCache

-0.47

なんと

-0.46

POSITIVE LOGITS

 person

0.96

 given

0.88

 persons

0.74

given

0.72

 adott

0.70

ils

0.69

 properly

0.68

 particular

0.67

 successful

0.67

iconque

0.67

Activations Density 0.558%

usage of the indefinite article "a" in diverse contexts

"a" followed by a noun

a followed by a word

No Comments

No Known Activations