INDEX

Explanations

terms related to small items or concepts in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 massive

-0.60

IsMutable

-0.59

 behe

-0.58

 giant

-0.58

 immen

-0.57

 Huge

-0.57

 mammoth

-0.57

 Massive

-0.56

 enormes

-0.56

Massive

-0.56

POSITIVE LOGITS

 small

1.72

 tiny

1.64

Small

1.57

 smaller

1.52

small

1.51

 diminutive

1.51

 Small

1.48

 SMALL

1.48

SMALL

1.39

 Tiny

1.38

Activations Density 0.931%

terms related to small items or concepts in various contexts

No Comments

No Known Activations