INDEX

Explanations

specific opening markers or indicators in the text

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

the start of a sentence or new section in the text

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

event management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.20.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

 متعلقه

-0.72

 Wikipedia

-0.66

andExpect

-0.63

 wikipedia

-0.57

wikipedia

-0.57

expandindo

-0.55

 nahilalakip

-0.55

IActionResult

-0.55

findpost

-0.52

>({

-0.52

POSITIVE LOGITS

 Event

1.07

Event

0.97

 EVENT

0.91

 event

0.84

event

0.82

EVENT

0.82

events

0.71

getEvent

0.70

survey

0.69

 ticketing

0.69

Activations Density 0.018%

specific opening markers or indicators in the text

the start of a sentence or new section in the text

event management

No Comments

No Known Activations