INDEX

Explanations

acronyms or initialisms, particularly those related to locations or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 senti

-0.51

Compar

-0.50

יפ

-0.49

יג

-0.48

━━━━━━━━

-0.47

<h2>

-0.46

куль

-0.46

 conta

-0.45

 integra

-0.44

rapp

-0.44

POSITIVE LOGITS

 kasarigan

1.19

 EconPapers

0.92

 propOrder

0.90

thâu

0.88

IUrlHelper

0.86

脚注の使い方

0.85

ThroughAttribute

0.85

PhysRev

0.85

Przypisy

0.85

+#+#

0.83

Activations Density 0.314%

acronyms or initialisms, particularly those related to locations or organizations

No Comments

No Known Activations