INDEX

Explanations

references to manual processes or tasks

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

torie

-0.71

glVertex

-0.67

omitempty

-0.66

yfik

-0.66

MEG

-0.66

belongs

-0.65

 CreateTagHelper

-0.65

 AssemblyProduct

-0.64

JsonInclude

-0.63

Dee

-0.63

POSITIVE LOGITS

 manual

2.13

 Manual

1.94

 MANUAL

1.86

MANUAL

1.83

Manual

1.82

manual

1.79

 manually

1.60

 manuel

1.55

 manuals

1.53

 manuale

1.53

Activations Density 0.098%

references to manual processes or tasks

No Comments

No Known Activations