INDEX

Explanations

terms related to loading processes and operations involving data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

Personendaten

-0.90

 plebis

-0.77

 Gorb

-0.75

انتهای

-0.72

aronder

-0.71

 étoient

-0.71

alnız

-0.71

XmlAccessorType

-0.71

 avoient

-0.71

 XIAOMI

-0.71

POSITIVE LOGITS

 Load

1.20

 load

1.19

LOAD

1.18

loads

1.16

load

1.16

Load

1.15

 loads

1.15

 LOAD

1.10

loaded

1.08

 loaded

1.06

Activations Density 0.073%

terms related to loading processes and operations involving data

No Comments

No Known Activations