INDEX

Explanations

terms related to statistical confidence intervals

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

Tokens related to intervals or bounds

np_acts-logits-general · gemini-2.0-flash

confidence intervals

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

 Waray

-0.54

شهاد

-0.54

لیس

-0.54

WriteLiteral

-0.54

 whiteColor

-0.53

gridy

-0.53

 Bobo

-0.51

 cadence

-0.48

ReusableCell

-0.48

PyExc

-0.47

POSITIVE LOGITS

 range

1.16

范围

1.00

range

0.99

 bounds

0.97

範囲

0.97

 boundaries

0.96

 ranges

0.96

 Range

0.95

 RANGE

0.91

範圍

0.91

Activations Density 0.982%

terms related to statistical confidence intervals

Tokens related to intervals or bounds

confidence intervals

No Comments

No Known Activations