INDEX

Explanations

terms and concepts related to psychology and mental health

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Multi

-0.39

SuppressLint

-0.39

wissenschaften

-0.38

springen

-0.36

 beans

-0.35

 AssemblyCulture

-0.35

 slime

-0.35

 hiszen

-0.35

 Busy

-0.34

Sli

-0.34

POSITIVE LOGITS

httphttps

0.64

 препратки

0.59

 betweenstory

0.50

 meditative

0.50

 HomeController

0.49

exitRule

0.48

########.

0.48

 IconData

0.47

 contemplative

0.45

缓慢

0.44

Activations Density 0.101%

terms and concepts related to psychology and mental health

No Comments

No Known Activations