INDEX

Explanations

affirmative or negative responses in the context of questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

[*]

-0.63

 aidant

-0.60

webElement

-0.58

enumii

-0.49

},{

-0.48

UIControlState

-0.47

 esetén

-0.45

 nữa

-0.45

 memoized

-0.45

isting

-0.44

POSITIVE LOGITS

RegistryLite

0.70

IActionResult

0.67

YES

0.61

Yes

0.60

 resourceCulture

0.58

addCriterion

0.58

matchCondition

0.57

 VizieR

0.57

}{@

0.56

AndroidJUnit

0.55

Activations Density 0.329%

affirmative or negative responses in the context of questions

No Comments

No Known Activations