INDEX

Explanations

references to 'elements' and 'components' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 GenerationType

-0.86

 Chry

-0.81

FAP

-0.80

cuses

-0.80

UpInside

-0.80

rawQuery

-0.79

chability

-0.78

 blanches

-0.77

pausal

-0.76

SwingConstants

-0.76

POSITIVE LOGITS

 elements

1.20

 element

1.16

Element

1.09

 Elements

1.09

Elements

1.08

 Element

1.05

 ELEMENT

1.02

IElement

1.01

elements

1.00

ELEMENT

1.00

Activations Density 0.065%

references to 'elements' and 'components' in various contexts

No Comments

No Known Activations