INDEX

Explanations

phrases indicating the significance or importance of various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

filepath

-0.51

tagHelperRunner

-0.50

bnf

-0.49

listdir

-0.46

 trás

-0.46

WebControls

-0.45

TestingModule

-0.44

 actionPerformed

-0.44

JspWriter

-0.43

writeFieldEnd

-0.43

POSITIVE LOGITS

 significance

0.94

 importance

0.93

 considerable

0.81

 consequence

0.81

 nature

0.79

 relevance

0.77

importance

0.75

 repute

0.75

 magnitude

0.75

 SIGNIFIC

0.73

Activations Density 0.243%

phrases indicating the significance or importance of various subjects

No Comments

No Known Activations