INDEX

Explanations

references to oil and its associated terms

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

oil or the oil industry

np_acts-logits-general · gemini-2.0-flash

oil and industry

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

पया

-0.64

 pous

-0.61

AutoresizingMask

-0.59

tun

-0.57

teps

-0.56

 Ingo

-0.54

 Attribution

-0.54

.$

-0.53

 Unger

-0.53

 Cuth

-0.53

POSITIVE LOGITS

OIL

0.74

 Oils

0.72

Oil

0.71

 oils

0.70

OIL

0.69

oil

0.67

cloth

0.67

Oil

0.66

 slick

0.64

 Oilers

0.63

Activations Density 0.070%

references to oil and its associated terms

oil or the oil industry

oil and industry

No Comments

No Known Activations