INDEX

Explanations

related to feedback requests and communication

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

The token "Ben" or similar variations

np_acts-logits-general · gemini-2.0-flash

words starting with "Ben"

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

Aer

-0.57

 Ogre

-0.56

Sod

-0.55

 Somers

-0.55

 Miroslav

-0.54

 Cuer

-0.54

 Carroll

-0.53

Asi

-0.52

 Pele

-0.52

Aer

-0.51

POSITIVE LOGITS

Ben

3.23

Ben

3.03

BEN

2.84

ben

2.58

BEN

2.54

ben

2.39

 Benjamin

2.04

 Бен

2.00

 Bens

1.90

Benjamin

1.89

Activations Density 0.133%

related to feedback requests and communication

The token "Ben" or similar variations

words starting with "Ben"

No Comments

No Known Activations