INDEX

Explanations

conditional statements and phrases

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

feinander

-0.68

 Darauf

-0.65

SAK

-0.63

extAlignment

-0.63

protoimpl

-0.59

[]>

-0.59

 Kanu

-0.57

***************/

-0.57

ึ้น

-0.57

complexContent

-0.57

POSITIVE LOGITS

 though

0.89

it

0.86

 Though

0.82

Though

0.80

Meski

0.76

 they

0.75

though

0.75

 despite

0.71

 Meski

0.70

the

0.69

Activations Density 0.012%

conditional statements and phrases

No Comments

No Known Activations