INDEX

Explanations

phrases related to obligation or expected actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

حات

-0.49

lacion

-0.47

layoutControl

-0.46

chester

-0.46

Anti

-0.45

 marty

-0.44

すると

-0.44

">//

-0.44

MouseEvent

-0.44

POSITIVE LOGITS

 shut

1.04

 SHUT

1.02

 Shut

1.00

Shut

0.96

shut

0.93

 stop

0.91

SHUT

0.87

 STOP

0.82

 Stop

0.81

 Roskov

0.77

Activations Density 0.250%

phrases related to obligation or expected actions

No Comments

No Known Activations