INDEX

Explanations

terms related to optimal configurations and conditions in various contexts, particularly relating to measurements and performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 EconPapers

-0.57

RenderAtEndOf

-0.52

 getItemId

-0.50

rifuge

-0.50

 للمعارف

-0.50

Oneof

-0.49

 isolada

-0.49

Begriffsklä

-0.49

erschutz

-0.48

Possibility

-0.48

POSITIVE LOGITS

絶妙

0.86

ちょうど

0.85

 ideal

0.72

 ideale

0.70

刚好

0.68

Perfectly

0.67

 perfect

0.66

 optimum

0.66

 Ideal

0.65

Ideal

0.65

Activations Density 0.591%

terms related to optimal configurations and conditions in various contexts, particularly relating to measurements and performance

No Comments

No Known Activations