INDEX

Explanations

expressions of personal opinions or beliefs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Diſ

-0.64

 pleaſure

-0.62

 Reſ

-0.58

 electrica

-0.57

Efq

-0.57

 houſe

-0.56

 Houſe

-0.54

 Inſ

-0.53

 Bede

-0.51

 devis

-0.50

POSITIVE LOGITS

 glaube

1.07

 probably

0.99

 chyba

0.92

Probably

0.88

ungkin

0.87

 probablemente

0.86

 creo

0.85

mutlich

0.85

 provavelmente

0.84

probably

0.83

Activations Density 0.072%

expressions of personal opinions or beliefs

No Comments

No Known Activations