INDEX

Explanations

references to academic titles and educational institutions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GOTREF

-0.57

addington

-0.54

issu

-0.53

acus

-0.52

abatic

-0.51

chii

-0.50

rative

-0.50

LLING

-0.50

IEU

-0.49

INGEN

-0.49

POSITIVE LOGITS

RegressionTest

0.70

 تضيفلها

0.58

 pymongo

0.58

Vidite

0.55

ThroughAttribute

0.54

openqa

0.52

Slf

0.49

WriteBarrier

0.49

 AspNetCore

0.48

0.47

Activations Density 0.175%

references to academic titles and educational institutions

No Comments

No Known Activations