INDEX

Explanations

phrases that indicate presence and functionality in a particular context

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

location changes or facilities

np_acts-logits-general · gemini-2.0-flash

location and relocation

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/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.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

تقاوى

-0.84

GEBURTSDATUM

-0.79

 AssemblyCulture

-0.78

abestanden

-0.77

LookAnd

-0.74

RenderAtEndOf

-0.74

 noDo

-0.73

EndContext

-0.72

InputTagHelper

-0.72

UrlResolution

-0.71

POSITIVE LOGITS

 location

0.81

 move

0.81

 relocated

0.80

 relocation

0.79

 relocate

0.79

 cramped

0.77

 relocating

0.74

location

0.73

 spacious

0.72

 Location

0.71

Activations Density 0.322%

phrases that indicate presence and functionality in a particular context

location changes or facilities

location and relocation

No Comments

No Known Activations

phrases that indicate presence and functionality in a particular context

location changes or facilities

location and relocation

No Comments

No Known Activations