INDEX

Explanations

opening phrases that indicate the start of a discussion or narrative

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

ributor

-0.53

िखित

-0.51

 باخ

-0.48

 pères

-0.48

classified

-0.46

áže

-0.44

 vícti

-0.44

chapper

-0.43

 Unclassified

-0.43

újo

-0.43

POSITIVE LOGITS

 however

0.94

 però

0.81

however

0.76

 όμως

0.74

However

0.73

 toutefois

0.73

 However

0.73

 azonban

0.71

 entanto

0.70

 jednak

0.69

Activations Density 0.516%

opening phrases that indicate the start of a discussion or narrative

No Comments

No Known Activations