INDEX

Explanations

programming-related keywords and structures in data processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.38.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

 auguri

-0.39

Kanpo

-0.39

 AssemblyCompany

-0.39

Története

-0.38

########.

-0.36

 lancar

-0.34

HostException

-0.33

hearsal

-0.33

 Würde

-0.33

 ROYAL

-0.32

POSITIVE LOGITS

df

1.39

df

1.21

pd

1.16

DF

1.10

 dataframe

1.06

 DataFrame

0.99

DataFrame

0.93

pd

0.90

DF

0.89

Df

0.88

Activations Density 0.354%

programming-related keywords and structures in data processing

No Comments

No Known Activations