INDEX

Explanations

code-related constructs and programming keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

ंदीखरीदारी

-0.52

letzt

-0.40

GraphicsUnit

-0.39

awtextra

-0.38

 >=",

-0.37

 full

-0.36

 Christiansen

-0.36

 kell

-0.35

ingly

-0.34

ądze

-0.34

POSITIVE LOGITS

 Demonstration

0.71

 demonstration

0.71

Demonstration

0.64

 demonstrate

0.63

 Demonstrate

0.61

 demonstrators

0.60

 demonstrating

0.58

 demonstr

0.58

 Demonstr

0.55

 demonstrates

0.55

Activations Density 1.570%

code-related constructs and programming keywords

No Comments

No Known Activations