INDEX

Explanations

references to decision-making and preference expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.37.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

 المعيارى

-0.64

 cliquant

-0.60

parsedMessage

-0.57

Traducción

-0.55

basicConfig

-0.54

RegressionTest

-0.53

 AssemblyVersion

-0.53

coping

-0.53

AsUp

-0.52

migrationBuilder

-0.50

POSITIVE LOGITS

 take

1.19

 make

1.15

 negotiate

1.06

 create

1.06

 give

1.05

 develop

1.04

 entertain

1.04

get

1.04

go

1.03

 move

1.03

Activations Density 3.481%

references to decision-making and preference expressions

No Comments

No Known Activations