INDEX

Explanations

terms related to decision-making processes

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 tags

-0.43

 hổ

-0.42

 Whit

-0.41

tags

-0.40

the

-0.40

 Bailey

-0.39

 büy

-0.39

ườ

-0.39

 turística

-0.39

 Merrick

-0.39

POSITIVE LOGITS

 decision

1.41

 decisions

1.34

 Decision

1.30

decision

1.30

 Decisions

1.27

Decision

1.26

Decisions

1.18

decisions

1.18

 DECISION

1.12

 décision

1.10

Activations Density 0.128%

terms related to decision-making processes

No Known Activations