INDEX

Explanations

code-related syntax and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Anſ

-0.86

 Majefty

-0.81

 iſt

-0.78

$:$

-0.78

Eſ

-0.75

\\

-0.73

 itſelf

-0.72

 Reſ

-0.72

ſelf

-0.71

 Houſe

-0.71

POSITIVE LOGITS

0.53

we

0.52

 gravedad

0.49

0.47

 mergeFrom

0.47

0.45

tencent

0.45

0.44

Activations Density 0.226%

code-related syntax and structures

No Comments

No Known Activations