INDEX

Explanations

phrases emphasizing user actions and personal engagement

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 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

ResumeLayout

-0.61



-0.60

EndInit

-0.59

Were

-0.55

+#+

-0.54

 Were

-0.54

#+#

-0.52

twimg

-0.47

pides

-0.47

Did

-0.46

POSITIVE LOGITS

can

3.39

can

2.27

Can

2.04

Can

1.97

 kann

1.63

 können

1.60

CAN

1.60

 dapat

1.58

可以

1.57

ecan

1.42

Activations Density 1.380%

phrases emphasizing user actions and personal engagement

No Comments

No Known Activations

phrases emphasizing user actions and personal engagement

No Comments

No Known Activations