INDEX

Explanations

elements related to file or app features and their functionalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

bootstrapcdn

-1.07

 pinulongan

-0.97

 فريبيس

-0.95

NUMX

-0.95

Tikang

-0.92

 rospy

-0.88

mybatisplus

-0.86

 crdi

-0.85

 iſt

-0.84

complexContent

-0.83

POSITIVE LOGITS

1.23

0.88

[toxicity=0]

0.83

<eos>

0.78

//

0.78

///

0.76

*),

0.76

<td>

0.75

*)

0.73

•

0.72

Activations Density 0.048%

elements related to file or app features and their functionalities

No Comments

No Known Activations