INDEX

Explanations

expressions or indicators of regulation and oversight in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

enumi

-0.95

 kasarigan

-0.88

OGND

-0.83

 ModelExpression

-0.83

 المعيارى

-0.79

 geslacht

-0.77

 Réponses

-0.74

 eventdata

-0.72



-0.68

="#"><

-0.65

POSITIVE LOGITS

Conversely

0.55

 meanwhile

0.50

 Conversely

0.49

rabh

0.48

 Meanwhile

0.48

elif

0.45

ranean

0.45

Similarly

0.45

 Likewise

0.44

diendo

0.43

Activations Density 0.380%

expressions or indicators of regulation and oversight in various contexts

No Comments

No Known Activations