INDEX

Explanations

references to information in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.34.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

 GenerationType

-0.45

 defaultstate

-0.44

limard

-0.37

Referanser

-0.37

 arşivlendi

-0.35

ⓧ

-0.35

 CascadeType

-0.35

JvmStatic

-0.34

userDao

-0.34

HSC

-0.34

POSITIVE LOGITS

 getInfo

0.72

 Information

0.71

Information

0.65

 information

0.64

 info

0.60

INFORMATION

0.60

 Info

0.59

 INFORMATION

0.58

 infos

0.56

 信息

0.55

Activations Density 0.102%

references to information in various contexts

No Comments

No Known Activations