INDEX

Explanations

terms related to deployment 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 @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

ValueStyle

-0.61

المناصب

-0.52

Raycast

-0.52

település

-0.49

 Réponses

-0.49

 noted

-0.49

Statics

-0.48

hli

-0.48

 Messieurs

-0.47

born

-0.47

POSITIVE LOGITS

 deployment

0.68

 deploy

0.65

SequentialGroup

0.63

ль

0.63

CrossRef

0.61

 Deployment

0.61

strix

0.60

ScopeManager

0.59

wixt

0.58

 invul

0.58

Activations Density 0.096%

terms related to deployment in various contexts

No Comments

No Known Activations