INDEX

Explanations

function definitions and their return statements in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

ume

-0.45

hika

-0.44

setViewportView

-0.43

agu

-0.41

stretchr

-0.40

CASCADE

-0.40

+",

-0.40

heyd

-0.39

AFX

-0.39

PLEX

-0.39

POSITIVE LOGITS

 виправивши

0.85

 Roskov

0.79

spesies

0.66

arischen

0.61

 kasarigan

0.60

basicConfig

0.59

vedic

0.58

 rowspan

0.58

DeleteBehavior

0.57

CloseOperation

0.57

Activations Density 0.080%

function definitions and their return statements in code

No Comments

No Known Activations