INDEX

Explanations

directory-related keywords and terms

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

 pleaſure

-0.98

 Monfieur

-0.96

 Beſ

-0.89

 purpoſe

-0.87

 ſeveral

-0.87

 Anſ

-0.86

 Cumber

-0.84

 neceſſ

-0.84

 Nunn

-0.84

 Inſ

-0.82

POSITIVE LOGITS

dir

2.70

dir

2.58

Dir

2.41

Dir

2.27

DIR

2.03

DIR

1.92

 dirs

1.65

dirs

1.64

Dirs

1.38

Dirk

1.06

Activations Density 0.042%

directory-related keywords and terms

No Comments

No Known Activations