INDEX

Explanations

text inside parentheses along with surrounding punctuation

oai_token-act-pair · gemini-2.0-flash

tokens starting with an open parenthesis

np_token-act-pair-logits · gpt-4o-mini

(

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

-0.88

-0.73

van

-0.70

_.

-0.69

“

-0.69

-0.67

di

-0.66

sa

-0.65

de

-0.64

As

-0.64

POSITIVE LOGITS

 itſelf

1.25

 pleaſure

1.14

 ་་

1.13

ſelf

1.13

 uſed

1.10

 myſelf

1.09

 ―――――

1.08

 Majefty

1.06

 Jefus

1.06

 reaſon

1.06

Activations Density 2.627%

text inside parentheses along with surrounding punctuation

tokens starting with an open parenthesis

(

No Comments

No Known Activations