INDEX

Explanations

technical terminology related to graph theory and connectivity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

DeleteBehavior

-0.58

CodedInputStream

-0.57

principalColumn

-0.55

complexContent

-0.55

 femininas

-0.53

ęku

-0.51

ListModule

-0.50

hasErrors

-0.50

солю

-0.49

GoogleApiClient

-0.49

POSITIVE LOGITS

both

1.03

 both

1.02

Both

0.99

 Both

0.98

 beider

0.94

neither

0.90

BOTH

0.90

 neither

0.87

Ambos

0.86

 between

0.86

Activations Density 0.820%

technical terminology related to graph theory and connectivity

No Comments

No Known Activations