INDEX

Explanations

references to guilt and shame

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

numerusform

-0.67

اقت

-0.65

WriteTagHelper

-0.64

urlpatterns

-0.62

 VIAF

-0.62

 autorytatywna

-0.59

 MaterialApp

-0.58

monary

-0.57

cektir

-0.57

ignty

-0.57

POSITIVE LOGITS

 blame

1.18

 blamed

1.16

 Blame

1.11

blame

1.07

 blaming

1.04

 blames

1.03

 scolded

0.98

Blame

0.97

 guilt

0.89

 reproach

0.83

Activations Density 0.244%

references to guilt and shame

No Comments

No Known Activations