INDEX

Explanations

enumerated lists and items in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

gne

-0.60

agna

-0.58

 onData

-0.57

CloseOperation

-0.57

 Vigo

-0.56

 whit

-0.55

sab

-0.54

 Palest

-0.53

gim

-0.52

SHA

-0.52

POSITIVE LOGITS

ii

2.86

iii

2.20

ii

2.00

iiiii

1.71

iiii

1.66

iii

1.53

vii

1.32

ⅱ

1.26

iiiiiiii

1.23

sii

1.22

Activations Density 0.096%

enumerated lists and items in a structured format

No Comments

No Known Activations