INDEX

Explanations

phrases indicating causality or outcomes

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

pherd

-0.72

 teach

-0.69

ToUse

-0.69

 abusing

-0.68

DotNetBar

-0.67

Dak

-0.66

 expandable

-0.66

 hates

-0.63

ppery

-0.63

 cometer

-0.63

POSITIVE LOGITS

 result

1.80

 resulted

1.67

 results

1.59

 resulting

1.57

 Result

1.56

 RESULT

1.52

result

1.49

Result

1.38

 résult

1.37

RESULT

1.37

Activations Density 0.136%

phrases indicating causality or outcomes

No Comments

No Known Activations