INDEX

Explanations

references to small objects or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

-0.49

 lusso

-0.46

 exposiciones

-0.44

umab

-0.44

closedir

-0.44

vez

-0.43

 eterno

-0.42

嫁

-0.42

↵↵

-0.41

POSITIVE LOGITS

 small

1.05

 MainAxisSize

1.03

small

1.02

Small

1.02

 SMALL

1.01

 Small

0.96

 ſmall

0.95

 smal

0.94

 Kecil

0.91

 Smaller

0.89

Activations Density 1.005%

references to small objects or concepts

No Comments

No Known Activations