INDEX

Explanations

statistical variations and differences in data across multiple categories or populations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

страция

-0.41

xil

-0.41

 terceiros

-0.40

必

-0.39

ʖ

-0.39

شرين

-0.37

Safe

-0.36

rex

-0.36

Foy

-0.36

usercontent

-0.36

POSITIVE LOGITS

 varying

1.17

 vary

1.13

 varies

1.12

 differing

1.11

 Vary

1.06

 differences

1.04

 variation

1.03

 depending

1.03

 different

1.03

 Variation

0.99

Activations Density 0.838%

statistical variations and differences in data across multiple categories or populations

No Comments

No Known Activations