INDEX

Explanations

terms related to software updates and changes in features

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

\{\\

-0.69

expandindo

-0.63

trường

-0.60

 незавершена

-0.59

 prefeito

-0.57

 فريبيس

-0.57

SPATH

-0.56

AndEndTag

-0.56

χεία

-0.55

 détruire

-0.55

POSITIVE LOGITS

 improved

0.83

improved

0.77

 expanded

0.71

Improved

0.70

 Improved

0.69

 improve

0.68

 increased

0.65

 expand

0.64

 clearer

0.63

 revised

0.62

Activations Density 0.430%

terms related to software updates and changes in features

No Comments

No Known Activations