INDEX

Explanations

function calls and method definitions 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 @ 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

EnableWeb

-0.83

ItemBackground

-0.74

HostException

-0.74

rrggbb

-0.72

 betweenstory

-0.72

InitVars

-0.71

bcrypt

-0.69

istoitu

-0.68

 pinulongan

-0.68

NameInMap

-0.67

POSITIVE LOGITS

defineProperty

0.71

 among

0.53

memberOf

0.47

amme

0.45

бю

0.43

 fully

0.43

makeText

0.43

 specifically

0.43

 visually

0.43

 profusely

0.42

Activations Density 0.272%

function calls and method definitions in code

No Comments

No Known Activations