INDEX

Explanations

terms related to approval and consent

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

-0.70

-0.62

-0.60

-0.59

ya

-0.58

tra

-0.58

be

-0.57

Ash

-0.57

 Jack

-0.57

POSITIVE LOGITS

 approvals

1.42

 Approval

1.36

 approval

1.33

 approve

1.31

 approving

1.31

 approves

1.28

approval

1.21

 Approve

1.21

 disapproval

1.18

Approval

1.16

Activations Density 0.110%

terms related to approval and consent

No Comments

No Known Activations