INDEX

Explanations

terms related to actions and transactions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 itſelf

-1.34

ſelf

-1.22

 myſelf

-1.21

ſelves

-1.17

 ་་

-1.10

 Monfieur

-1.09

 themſelves

-1.09

 ſind

-1.03

 himſelf

-1.03

 unſ

-1.02

POSITIVE LOGITS

0.73

0.70

0.68

la

0.64

0.63

0.61

the

0.60

0.59

cu

0.58

so

0.58

Activations Density 0.475%

terms related to actions and transactions in various contexts

No Comments

No Known Activations