INDEX

Explanations

references to confirmation or verification actions

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

verwijspagina

-1.09

 ExecuteAsync

-0.86

rungsseite

-0.84

 moschino

-0.84

 Савезне

-0.81

ernalia

-0.78

riction

-0.74

%");

-0.73

 Normdatei

-0.73

WithIdentifier

-0.71

POSITIVE LOGITS

 же

0.76

 их

0.71

 also

0.67

tagHelper

0.64

 sich

0.64

je

0.64

 нас

0.62

Его

0.60

 juga

0.60

 них

0.60

Activations Density 0.023%

references to confirmation or verification actions

No Comments

No Known Activations