INDEX

Explanations

references to events or activities

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

Punctuations and symbols

np_acts-logits-general · gemini-2.0-flash

trekking and scenic views

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

AddTagHelper

-0.83

tagHelperRunner

-0.79

styleType

-0.72

ValueStyle

-0.68

 незавершена

-0.66

 الحره

-0.65

})->

-0.64

saraba

-0.62

LEncoder

-0.61

WithIOException

-0.60

POSITIVE LOGITS

 hill

0.73

 trek

0.68

 greenery

0.66

 scenic

0.62

 trekking

0.62

 tourist

0.59

 picturesque

0.58

 Corbett

0.58

Trek

0.57

 sightseeing

0.57

Activations Density 0.067%

references to events or activities

Punctuations and symbols

trekking and scenic views

No Comments

No Known Activations