INDEX

Explanations

mentions of notable names or titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 itſelf

-2.12

 myſelf

-1.84

 Theſe

-1.72

 ་་

-1.71

ſelf

-1.71

 Houſe

-1.67

 purpoſe

-1.64

 iſt

-1.63

BibitemShut

-1.62

 reaſon

-1.60

POSITIVE LOGITS

0.94

Ar

0.94

0.92

Ar

0.90

0.89

op

0.88

li

0.87

Activations Density 0.974%

mentions of notable names or titles

No Comments

No Known Activations