INDEX

Explanations

references to rings and jewelry, particularly diamonds and their symbolism

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 transfieras

-0.93

SourceChecksum

-0.84

MLLoader

-0.79

TagMode

-0.77

رشف

-0.75

atrième

-0.73

 mourut

-0.71

Posters

-0.70

DockStyle

-0.67

 surla

-0.66

POSITIVE LOGITS

 jewelry

1.24

 ring

1.21

 diamonds

1.18

 rings

1.13

 diamond

1.11

 Diamonds

1.06

 Diamond

1.05

diamonds

1.05

 jewel

1.05

 Ring

1.04

Activations Density 0.286%

references to rings and jewelry, particularly diamonds and their symbolism

No Comments

No Known Activations