INDEX

Explanations

references to the term "Pat" and its variations in terms of usage and context

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

"Pat" or "pat" and its variations

np_acts-logits-general · gemini-2.0-flash

words starting with pat

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 gynhyrchwyd

-0.69

twimg

-0.67

 Meksiku

-0.62

BeginContext

-0.62

ChildScrollView

-0.62

 MonoBehaviour

-0.61

 noqa

-0.60

SpringRunner

-0.60

audiovisuel

-0.59

 esternos

-0.59

POSITIVE LOGITS

PAT

0.89

Pat

0.80

PAT

0.79

pat

0.79

Pat

0.72

 Pats

0.70

 pats

0.67

Pats

0.64

pat

0.63

 patterns

0.60

Activations Density 0.141%

references to the term "Pat" and its variations in terms of usage and context

"Pat" or "pat" and its variations

words starting with pat

No Comments

No Known Activations