INDEX

Explanations

references to definitions, descriptions, and classifications within structured information or formal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

hyrchwyd

-0.71

 auffi

-0.67

TagMode

-0.67

 ſeveral

-0.64

исленность

-0.64

elemField

-0.63

DataAnnotations

-0.63

AndEndTag

-0.63

tidaknya

-0.62

 >=",

-0.62

POSITIVE LOGITS

hasiswa

0.56

ípio

0.49

cms

0.46

brainly

0.45

 году

0.45

 winner

0.45

day

0.44

cms

0.43

guy

0.42

 Industries

0.41

Activations Density 1.109%

references to definitions, descriptions, and classifications within structured information or formal contexts

No Comments

No Known Activations