INDEX

Explanations

terms related to concrete and brick materials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 goutte

-0.82

 odeur

-0.80

Personensuche

-0.77

 Monfieur

-0.75

 Venise

-0.75

 myſelf

-0.74

usepackage

-0.73

 Unidas

-0.73

 defoli

-0.73

 argint

-0.73

POSITIVE LOGITS

 bricks

1.15

 brick

1.12

 Brick

1.07

Brick

1.02

bricks

0.99

brick

0.96

 Bricks

0.93

 cement

0.90

Bricks

0.90

 concrete

0.84

Activations Density 0.158%

terms related to concrete and brick materials

No Comments

No Known Activations