INDEX

Explanations

class and constructor definitions in programming code

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

old

-0.51

spunk

-0.50

fromnode

-0.49

累

-0.47

 scre

-0.46

inSlope

-0.46

EDEFAULT

-0.45

awtextra

-0.44

šanās

-0.44

킷

-0.43

POSITIVE LOGITS

uxxxx

0.79

MockBean

0.73

 Meksiku

0.72

Autowired

0.68

adpleegd

0.63

ActionCreators

0.63

 للمعارف

0.63

providedIn

0.62

optarg

0.61

StoryboardSegue

0.60

Activations Density 0.046%

class and constructor definitions in programming code

No Comments

No Known Activations