INDEX

Explanations

the word "towards" and its variations, and words and phrases describing direction

oai_token-act-pair · gemini-2.0-flash

direction

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

 Normdatei

-0.64

Clik

-0.61

 setTotal

-0.54

Rujuakan

-0.53

 encarga

-0.53

Ӏ

-0.52

 ExecuteAsync

-0.52

ulted

-0.52

ANSION

-0.51

cipal

-0.51

POSITIVE LOGITS

towards

0.90

 toward

0.86

 towards

0.85

toward

0.85

 Towards

0.82

Towards

0.80

 Toward

0.70

Toward

0.70

hacia

0.66

TOW

0.63

Activations Density 1.419%

the word "towards" and its variations, and words and phrases describing direction

direction

No Comments

No Known Activations