INDEX

Explanations

references to institutions and organizations

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

Following "the" in location names

np_acts-logits-general · gemini-2.0-flash

the [institution name]

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

 مشين

-0.88

tagHelperRunner

-0.76

 consultato

-0.72

 <<<<<<<<<<<<<<

-0.71

DoubleQuotes

-0.69

BufferException

-0.69

TypedDataSet

-0.66

 disambiguazione

-0.65

 Lightboxes

-0.65

 snippetHide

-0.62

POSITIVE LOGITS

InstanceState

0.56

apolis

0.54

Ne

0.51

憐

0.50

ETTI

0.50

achusetts

0.50

 prestigious

0.50

 thriving

0.48

Tra

0.48

INTE

0.47

Activations Density 0.371%

references to institutions and organizations

Following "the" in location names

the [institution name]

No Comments

No Known Activations