INDEX

Explanations

terms related to additional processes or components in a procedure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

InjectAttribute

-0.50

 hadiah

-0.45

 eneste

-0.45

DebuggerNonUser

-0.44

En

-0.44

 defaultstate

-0.43

enein

-0.42

 bäst

-0.41

せ

-0.41

斑

-0.41

POSITIVE LOGITS

 nakalista

0.83

AsUp

0.72

+#+#

0.72

 betweenstory

0.70

 تانيه

0.70

transQ

0.69

:]:

0.68

vábbi

0.67

 חיצוניים

0.66

 ועוד

0.65

Activations Density 0.725%

terms related to additional processes or components in a procedure

No Comments

No Known Activations