INDEX

Explanations

occurrences of indefinite articles and related quantifiers in sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

-0.66

↵↵

-0.57

<eos>

-0.48

↵

-0.45

van

-0.44

つもり

-0.44

赛

-0.42

-0.41

ศ

-0.41

off

-0.41

POSITIVE LOGITS

 ſtate

1.09

 itſelf

1.08

 myſelf

1.07

 pleaſure

1.04

 Shakspeare

1.02

 disambiguazione

1.01

 Chriftian

1.01

 Jefus

1.00

 ſeveral

0.98

 purpoſe

0.97

Activations Density 0.442%

occurrences of indefinite articles and related quantifiers in sentences

No Comments

No Known Activations