INDEX

Explanations

subjective intensifiers of opinion

oai_token-act-pair · gemini-2.0-flash

phrases related to legal terms and contexts

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

intensifiers

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

engagent

-0.76

 GenerationType

-0.73

ArgsConstructor

-0.68

 esternos

-0.65

 للاسماء

-0.62

 <=",

-0.61

Notae

-0.60

 testé

-0.60

windowFixed

-0.59

 TextAlign

-0.59

POSITIVE LOGITS

shift

0.54

 connexes

0.50

DoubleQuotes

0.47

 saper

0.44

 कैसी

0.44

("${

0.44

 shift

0.43

cord

0.42

amento

0.42

 ché

0.41

Activations Density 1.634%

subjective intensifiers of opinion

phrases related to legal terms and contexts

intensifiers

No Comments

No Known Activations