INDEX

Explanations

terms and phrases related to policies and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

The

-0.44

find

-0.41

Find

-0.41

from

-0.40

________________

-0.40

 mystérie

-0.39

 узна

-0.38

 kapturem

-0.38

 dziewczyn

-0.38

 mieszkań

-0.38

POSITIVE LOGITS

 policy

1.80

 POLICY

1.74

 Policy

1.68

policy

1.65

Policy

1.60

POLICY

1.52

 policies

1.52

 Policies

1.45

Policies

1.39

 POLICIES

1.35

Activations Density 0.119%

terms and phrases related to policies and regulations

No Comments

No Known Activations