INDEX

Explanations

instances of the word "confirm" 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 @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

-0.69

Rok

-0.69

enzie

-0.65

Rok

-0.64

Sk

-0.62

-0.60

lauf

-0.60

angelo

-0.60

tas

-0.60

She

-0.60

POSITIVE LOGITS

 Confirm

1.34

 confirmations

1.34

 verifies

1.26

 Confirmation

1.25

 confirms

1.22

irms

1.21

 Confirmed

1.20

CONFIRM

1.19

 confirm

1.16

 confirmation

1.16

Activations Density 0.170%

instances of the word "confirm" in various contexts

No Comments

No Known Activations