INDEX

Explanations

terms related to upper and lower bounds in mathematical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 Réponses

-1.17

DMG

-0.79

 Argos

-0.78

 Params

-0.77

 Walkover

-0.76

 Dandy

-0.76

 Carrasco

-0.76

xFE

-0.73

 requestId

-0.72

Vorte

-0.72

POSITIVE LOGITS

Lower

1.17

 Lower

1.12

 Upper

1.12

 LOWER

1.10

LOWER

1.08

 lower

1.07

 UPPER

1.07

Upper

1.05

UPPER

1.05

 upper

1.02

Activations Density 0.106%

terms related to upper and lower bounds in mathematical contexts

No Comments

No Known Activations