INDEX

Explanations

the prefix "pre-"

oai_token-act-pair · gemini-2.0-flash

pre

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 satunya

-0.60

LowerCase

-0.57

-0.56

 tiež

-0.55

-0.52

 věci

-0.52

 mourir

-0.51

 assume

-0.49

Man

-0.49

POSITIVE LOGITS

 myſelf

1.27

 pleaſure

1.07

 themſelves

1.07

 itſelf

1.05

 ſeveral

1.05

uſ

1.04

 ſhe

1.02

 theſe

1.00

 ſta

1.00

 himſelf

1.00

Activations Density 1.161%

the prefix "pre-"

pre

No Known Activations