INDEX

Explanations

words related to verification and confirmation processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pás

-0.53

 epä

-0.51

opardy

-0.51

 Lázaro

-0.50

PPS

-0.49

 pinulongan

-0.49

 Garry

-0.48

Strict

-0.47

lık

-0.47

ativní

-0.47

POSITIVE LOGITS

__":

0.91

__':

0.81

__":

0.81

__':

0.79

iecie

0.74

(!__

0.73

],\

0.71

 AssemblyProduct

0.70

менте

0.70

.*")]

0.66

Activations Density 0.030%

words related to verification and confirmation processes

No Comments

No Known Activations