INDEX

Explanations

references to oil and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

GraphicsUnit

-0.89

zookeeper

-0.82

makeConstraints

-0.76

StructEnd

-0.75

 Picchu

-0.74

CSC

-0.71

becca

-0.71

 Rask

-0.70

 rospy

-0.68

 Vener

-0.67

POSITIVE LOGITS

oil

1.80

Oil

1.74

OIL

1.72

 oils

1.63

 Oils

1.62

Oil

1.61

oil

1.53

OIL

1.50

 oiled

1.27

 olie

1.26

Activations Density 0.128%

references to oil and related concepts

No Comments

No Known Activations