INDEX

Explanations

references to specific rows in a dataset or table structure

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

row index or position

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Schweitzer

-0.58

Aga

-0.56

Aga

-0.55

 Opti

-0.53

Cib

-0.52

fortawesome

-0.52

Particular

-0.52

Opti

-0.51

might

-0.50

 Gladstone

-0.50

POSITIVE LOGITS

Row

1.07

Row

1.05

row

1.03

row

0.98

 Rows

0.94

setRow

0.94

ROW

0.94

 rows

0.93

 numberOfRows

0.91

getRow

0.87

Activations Density 0.015%

references to specific rows in a dataset or table structure

row index or position

No Comments

No Known Activations