INDEX

Explanations

negative phrases or concepts that indicate lack or inability

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

adpleegd

-0.87

ValueStyle

-0.80

 ISNI

-0.73

 springfox

-0.70

twimg

-0.69

 Signalez

-0.68

rawDesc

-0.67

 Exacts

-0.67

msgSender

-0.64

 للمعارف

-0.64

POSITIVE LOGITS

__':

0.53

 sondern

0.52

"])

0.48

нциклопедия

0.47

?>"

0.47

 ")");

0.46

ferrer

0.45

 otherwise

0.44

เต็ม

0.43

ائل

0.43

Activations Density 0.152%

negative phrases or concepts that indicate lack or inability

No Comments

No Known Activations