INDEX

Explanations

terms related to classification and descriptiveness 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 @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

neté

-0.99

 nahilalakip

-0.96

IUrlHelper

-0.94

 disponibilités

-0.91

AutoScaleMode

-0.90

})]

-0.90

 '\\;'

-0.89

ostante

-0.88

Personendaten

-0.87

دانشنامهٔ

-0.86

POSITIVE LOGITS

er

1.70

ه

1.70

1.67

1.58

1.49

1.39

en

1.14

ה

1.05

ي

1.04

Activations Density 1.300%

terms related to classification and descriptiveness in various contexts

No Comments

No Known Activations