INDEX

Explanations

references to plastic and related materials

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

]")]

-0.98

InSection

-0.98

 AssemblyCulture

-0.96

EqualsAnd

-0.91

NamedQueries

-0.89

WebVitals

-0.89

hoeddwyd

-0.87

__":

-0.86

 secco

-0.85

ocere

-0.85

POSITIVE LOGITS

 Plastic

1.41

 plastic

1.41

Plastic

1.38

 plastics

1.33

plastic

1.29

 PLASTIC

1.26

 Plastics

1.19

Plas

1.17

 Plastik

1.14

 Plas

1.13

Activations Density 0.086%

references to plastic and related materials

No Known Activations