INDEX

Explanations

negative responses or doubts about content and understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 للمعارف

-0.80

 متعلقه

-0.69

RenderAtEndOf

-0.57

 '/';

-0.55

__);

-0.52

]--;

-0.52

.*")]

-0.51

WEBPACK

-0.49

ollett

-0.49

esModule

-0.48

POSITIVE LOGITS

 neither

2.37

neither

2.12

 Neither

1.95

 nothing

1.93

 none

1.90

Neither

1.84

 nowhere

1.70

 None

1.66

None

1.63

 nobody

1.60

Activations Density 0.130%

negative responses or doubts about content and understanding

No Comments

No Known Activations