INDEX

Explanations

punctuation and basic grammatical structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

rungsseite

-0.86

 tartalomajánló

-0.85

 kaarangay

-0.79

сылкі

-0.74

tagHelperRunner

-0.74

IUrlHelper

-0.72

contentLoaded

-0.69

 gynhyrchwyd

-0.69

 Phoen

-0.69

UpInside

-0.69

POSITIVE LOGITS

 commonly

0.49

OCCURRED

0.48

commonly

0.47

 bekend

0.46

рани

0.45

PMailer

0.45

conoc

0.44

Sidenav

0.43

idig

0.43

 Rudd

0.43

Activations Density 0.590%

punctuation and basic grammatical structures

No Comments

No Known Activations