INDEX

Explanations

contexts where relationships or concepts are being illustrated or explained

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 None

-0.53

 These

-0.49

外部

-0.45

apiClient

-0.45

 none

-0.45

Campe

-0.45

The

-0.44

чел

-0.44

kozá

-0.44

 intptr

-0.43

POSITIVE LOGITS

 disambiguazione

0.93

 gynhyrchwyd

0.80

 IBOutlet

0.79

elyk

0.78

vernight

0.77

 CreateTagHelper

0.77

 myſelf

0.77

DockStyle

0.76

 esternos

0.75

WriteTagHelper

0.74

Activations Density 0.204%

contexts where relationships or concepts are being illustrated or explained

No Comments

No Known Activations