INDEX

Explanations

segments related to data structures or programming syntax

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

x_{

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 continúas

-0.78

 متعلقه

-0.66

 snippetHide

-0.63

Tep

-0.61

 Brin

-0.60

AccessorTable

-0.59

Datuak

-0.59

tagHelperRunner

-0.58

værende

-0.58

__((

-0.57

POSITIVE LOGITS

 الحره

0.55

sibirsk

0.55

 StringTokenizer

0.52

 disponibilités

0.50

ichio

0.50

rophoto

0.50

المكان

0.48

IntoConstraints

0.47

出版年

0.47

 Soni

0.46

Activations Density 0.087%

segments related to data structures or programming syntax

x_{

No Comments

No Known Activations