INDEX

Explanations

the word "off" and words conceptually related to removal

oai_token-act-pair · gemini-2.0-flash

Removal

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

LookAnd

-0.63

CodeDom

-0.54

DebuggerStep

-0.51

diğini

-0.50

Activités

-0.50

 nakalista

-0.50

 contd

-0.50

 Gual

-0.49

 BoxDecoration

-0.49

ContentAsync

-0.49

POSITIVE LOGITS

 REMOVE

0.78

REMOVE

0.77

 Remove

0.76

 remove

0.75

 khỏi

0.72

 removes

0.72

 Removing

0.71

Removes

0.70

 removed

0.70

 Remover

0.70

Activations Density 1.438%

the word "off" and words conceptually related to removal

Removal

No Comments

No Known Activations