INDEX

Explanations

words that mean conflict

oai_token-act-pair · gemini-2.0-flash

fight

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

Not in Any Lists

No Comments

Negative Logits

 myſelf

-2.39

 Monfieur

-2.25

Efq

-2.25

 purpoſe

-2.20

 pleaſure

-2.19

 itſelf

-2.17

 themſelves

-2.11

ſelves

-2.09

 Jefus

-2.08

 houſe

-2.06

POSITIVE LOGITS

the

1.16

1.09

↵↵

1.09

↵

1.05

...

1.04

1.00

<eos>

0.99

in

0.97

0.96

Activations Density 2.059%

words that mean conflict

fight

No Comments

No Known Activations