INDEX

Explanations

patterns indicative of lists or structured data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

IntentFilter

-0.56

Архівовано

-0.54

PRNewswire

-0.49

WriteTagHelper

-0.47

iency

-0.46

 besk

-0.45

addPreferredGap

-0.45

bá

-0.44

itespace

-0.43

koz

-0.43

POSITIVE LOGITS

 tartalomajánló

0.81

thâu

0.71

 ostavi

0.69

 AssemblyVersion

0.67

+#+#

0.67

WebServlet

0.66

MigrationBuilder

0.65

 OFDb

0.65

 Lamp

0.63

 Paglinawan

0.63

Activations Density 0.494%

patterns indicative of lists or structured data

No Comments

No Known Activations