INDEX

Explanations

words related to decision-making and arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 getF

-0.61

 warmest

-0.59

$__

-0.57

byter

-0.57

atisk

-0.57

rza

-0.56

énario

-0.56

XB

-0.55

LabelTagHelper

-0.54

__":

-0.54

POSITIVE LOGITS

 referrerpolicy

0.68

 with

0.65

in

0.63

UnsafeEnabled

0.59

 indisponible

0.54

Santis

0.53

 through

0.53

 about

0.53

or

0.52

on

0.52

Activations Density 1.002%

words related to decision-making and arguments

No Comments

No Known Activations