INDEX

Explanations

occurrences of the letter 'd' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

SourceChecksum

-0.73

hæ

-0.60

 determin

-0.56

Duff

-0.54

 نش

-0.52

بوابة

-0.52

BUN

-0.52

uncher

-0.51

 aprovecha

-0.51

Портал

-0.51

POSITIVE LOGITS

2.68

2.09

ｄ

1.41

д

1.03

getD

1.00

dS

0.99

dR

0.91

𝑑

0.89

𝐝

0.88

dP

0.86

Activations Density 0.162%

occurrences of the letter 'd' in various contexts

No Comments

No Known Activations