INDEX

Explanations

terms related to aggressive behavior and corporate contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 HIER

-0.44

 Vail

-0.40

 tutela

-0.37

 fianco

-0.36

 Hierarchy

-0.36

 Sage

-0.35

yAxis

-0.35

 opleiding

-0.35

 trilogy

-0.34

 diagon

-0.34

POSITIVE LOGITS

 Johnny

1.13

Johnny

1.09

Danny

1.05

 Danny

1.04

Tommy

1.02

 Tommy

0.99

 johnny

0.88

 Bobby

0.87

Bobby

0.87

 Joey

0.83

Activations Density 0.121%

terms related to aggressive behavior and corporate contexts

No Comments

No Known Activations