INDEX

Explanations

mathematical symbols and notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 betreft

-0.69

 Réponses

-0.66

☸

-0.65

 chi̍t

-0.65

 NSCoder

-0.64

 AssemblyTitle

-0.63

VIAF

-0.63

ClientSize

-0.61

ően

-0.61

 fleste

-0.60

POSITIVE LOGITS

tvguidetime

0.75

{#

0.73

\{\\

0.69

 Guen

0.67

 فريبيس

0.66

0.63

 insuffisamment

0.63

googleapis

0.61

enumii

0.59

dania

0.58

Activations Density 0.026%

mathematical symbols and notation

No Comments

No Known Activations