INDEX

Explanations

words and phrases related to institutions, categories, rankings, and professions

oai_token-act-pair · gemini-2.0-flash

among or etc

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

-1.00

 itſelf

-0.89

 raiſ

-0.82

 iſt

-0.81

 themſelves

-0.81

 preſent

-0.80

 Monfieur

-0.79

 auffi

-0.78

 ſhe

-0.77

 ſtate

-0.77

POSITIVE LOGITS

 among

3.08

among

2.70

 amongst

2.53

etc

2.39

 AMONG

2.33

 Among

2.27

etc

2.11

Among

2.06

Etc

1.91

等

1.90

Activations Density 2.856%

words and phrases related to institutions, categories, rankings, and professions

among or etc

No Comments

No Known Activations