INDEX

Explanations

references to ambiguous or unspecified items, often framed as questions or reflections

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

curacy

-0.70

Datuak

-0.70

 Exile

-0.70

 Lait

-0.69

owohl

-0.68

chließend

-0.68

zbęd

-0.68

 Insets

-0.66

titian

-0.66

 âme

-0.66

POSITIVE LOGITS

 something

2.54

something

2.48

Something

2.43

 Something

2.36

 SOMETHING

2.13

 somethin

1.88

ETHING

1.73

Somebody

1.60

 algo

1.53

 somebody

1.50

Activations Density 0.065%

references to ambiguous or unspecified items, often framed as questions or reflections

No Comments

No Known Activations