INDEX

Explanations

terms related to programming functions and their associated operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.40.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

 Ejecutivo

-0.45

 Conferencia

-0.42

 Secretario

-0.42

 AssemblyCompany

-0.41

 Gemeinschaft

-0.40

 Particularly

-0.39

 genellikle

-0.39

 Including

-0.38

__':

-0.38

 menciptakan

-0.37

POSITIVE LOGITS

 info

0.80

id

0.76

 value

0.75

 item

0.74

 state

0.74

 status

0.72

 object

0.71

 data

0.70

 flag

0.68

 type

0.67

Activations Density 1.424%

terms related to programming functions and their associated operations

No Comments

No Known Activations