INDEX

Explanations

frequent occurrences of the character 'x' followed by various numerical values, indicating a focus on formatting or data 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

 snippetHide

-1.50

 ―――――

-1.49

 myſelf

-1.45

 itſelf

-1.36

 themſelves

-1.33

 pleaſure

-1.32

 doubtnut

-1.31

 Anſ

-1.31

تقاوى

-1.30

ſelf

-1.29

POSITIVE LOGITS

1.19

0.78

0.76

<i>

0.75

0.73

0.72

0.71

Activations Density 0.177%

frequent occurrences of the character 'x' followed by various numerical values, indicating a focus on formatting or data structures

No Comments

No Known Activations