INDEX

Explanations

references to large quantities or scales

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 small

-0.73

 large

-0.72

 kleines

-0.70

 pequeno

-0.68

tiny

-0.68

 небольшой

-0.67

 pequeñas

-0.67

large

-0.67

 pequenas

-0.66

 smaller

-0.66

POSITIVE LOGITS

 scale

0.99

 amounts

0.97

 quantities

0.90

 amount

0.82

scale

0.81

mouth

0.78

 numbers

0.76

ConstraintMaker

0.74

 Scale

0.74

amounts

0.73

Activations Density 0.398%

references to large quantities or scales

No Comments

No Known Activations