INDEX

Explanations

programming-related keywords and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 auroit

-0.73

 scattata

-0.72

 avoient

-0.71

Efq

-0.69

 feroit

-0.69

 <>",

-0.68

 Monfieur

-0.68

 griega

-0.67

 Paglinawan

-0.67

 moschino

-0.67

POSITIVE LOGITS

 build

0.56

IBAction

0.52

run

0.50

def

0.50

autre

0.50

'&:

0.49

lably

0.48

tra

0.47

 effect

0.46

DockStyle

0.46

Activations Density 0.073%

programming-related keywords and function definitions

No Comments

No Known Activations