INDEX

Explanations

concepts and ideas related to notions and arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 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

awk

-0.40

-------

-0.37

 sere

-0.36

@[+][

-0.36

RefNanny

-0.35

peper

-0.35

 ContentValues

-0.35

ประกอบ

-0.35

RTCF

-0.34

辅

-0.34

POSITIVE LOGITS

 kasarigan

0.60

NameInMap

0.58

 notion

0.50

 kvinnor

0.49

 <=",

0.49

 kvinder

0.47

 kesan

0.46

 Notion

0.45

そもそも

0.44

 MainAxisSize

0.44

Activations Density 0.738%

concepts and ideas related to notions and arguments

No Comments

No Known Activations