INDEX

Explanations

discussions on various topics and treatment approaches

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tercih

-0.53

 sanitaires

-0.51

 suspendu

-0.51

çe

-0.51

 reç

-0.48

 značky

-0.47

 lyder

-0.47

 Schluss

-0.47

 équip

-0.47

 dupla

-0.46

POSITIVE LOGITS

 discuss

1.14

 topics

1.11

 discusses

1.11

 discussing

1.06

 discussed

0.97

 Topics

0.94

 topic

0.92

discus

0.91

Discus

0.90

 membahas

0.90

Activations Density 0.454%

discussions on various topics and treatment approaches

No Comments

No Known Activations