INDEX

Explanations

terms related to scientific experimentation and methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

<bos>

-0.61

-0.56

as

-0.55

and

-0.50

-0.45

期刊论文

-0.45

-0.43

Kal

-0.42

Lie

-0.41

をし

-0.41

POSITIVE LOGITS

ValueStyle

0.76

 pleaſure

0.75

 purpoſe

0.73

setVerticalGroup

0.72

 preſent

0.69

 ſever

0.68

 myſelf

0.68

 Hift

0.67

 CreateTagHelper

0.66

 Conſ

0.65

Activations Density 1.040%

terms related to scientific experimentation and methodologies

No Comments

No Known Activations