INDEX

Explanations

phrases indicating ongoing actions or events in a narrative context

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

what is happening?

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

switch

-0.52

 Switch

-0.52

 basket

-0.50

Backbone

-0.47

 SWITCH

-0.46

 esse

-0.46

 MediaType

-0.46

selectBy

-0.45

 sonde

-0.45

чта

-0.44

POSITIVE LOGITS

 }}"></

0.86

GraphicsUnit

0.82

 disambiguazione

0.81

 AssemblyTitle

0.81

MessageTagHelper

0.75

__":

0.73

buttonBar

0.73

 متعلقه

0.71

 happening

0.70

=$?

0.69

Activations Density 0.047%

phrases indicating ongoing actions or events in a narrative context

what is happening?

No Comments

No Known Activations