INDEX

Explanations

co-occurring conjunctions and their usage in lists or comparisons

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

VersionUID

-0.69

AnchorStyles

-0.62

 CreateTagHelper

-0.61

 NSCoder

-0.59

 invokingState

-0.59

Chham

-0.57

 createState

-0.55

Diwedd

-0.53

SequentialGroup

-0.52

WriteTagHelper

-0.51

POSITIVE LOGITS

lusconi

0.55

abinieri

0.52

 alike

0.50



0.50

Välislingid

0.48

甚至

0.48

乃至

0.47

berra

0.47

mybatisplus

0.47

 vues

0.47

Activations Density 0.225%

co-occurring conjunctions and their usage in lists or comparisons

No Comments

No Known Activations