INDEX

Explanations

actions involving physical interaction or manipulation with objects or individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 FetchType

-0.63

 متعلقه

-0.63

AutoScaleMode

-0.60

queryInterface

-0.57

setVerticalGroup

-0.56

 跳转至

-0.55

createCell

-0.55

 voyageurs

-0.54

RTLD

-0.54

 Favor

-0.53

POSITIVE LOGITS

 inserted

0.72

 stabbed

0.68

 thrust

0.65

 poked

0.65

 protr

0.64

插入

0.64

 插入

0.63

 poking

0.63

 plugged

0.63

 MainAxisSize

0.62

Activations Density 0.214%

actions involving physical interaction or manipulation with objects or individuals

No Comments

No Known Activations