INDEX

Explanations

phrases that introduce reports or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 pleaſure

-0.78

 itſelf

-0.75

 increí

-0.74

 ſche

-0.69

 Reſ

-0.69

 Theſe

-0.68

 ſind

-0.68

 Anſ

-0.68

 ſeine

-0.67

 dieſer

-0.67

POSITIVE LOGITS

rivit

0.66

Secondo

0.65

 Secondo

0.65

 Según

0.65

Según

0.59

 según

0.58

 ifølge

0.58

según

0.57

ølge

0.56

Selon

0.54

Activations Density 0.158%

phrases that introduce reports or statements

No Comments

No Known Activations