INDEX

Explanations

terms related to system states and interactions in a programming or technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

querySelectorAll

-0.45

saraba

-0.41

 dual

-0.38

 marginal

-0.38

 impressive

-0.35

 Sucher

-0.34

GenerationType

-0.34

点点头

-0.34

Дереккөздер

-0.32

 margin

-0.32

POSITIVE LOGITS

expandindo

0.72

 purpoſe

0.71

IUrlHelper

0.69

transQ

0.67

 betweenstory

0.66

ſelves

0.65

 ſche

0.63

 uſed

0.62

 houſe

0.61

 myſelf

0.60

Activations Density 0.496%

terms related to system states and interactions in a programming or technical context

No Comments

No Known Activations