INDEX

Explanations

references to the minimum or least threshold in various contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

Following the word "least"

np_acts-logits-general · gemini-2.0-flash

at least or least

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

Negative Logits

 مشين

-1.01

Efq

-0.94

 Jefus

-0.82

ніципалі

-0.79

nodoc

-0.75

 Chrift

-0.74

例句

-0.72

 Diſ

-0.72

ⓧ

-0.71

essica

-0.71

POSITIVE LOGITS

 least

0.84

jmniej

0.63

minHeight

0.59

 atleast

0.57

Least

0.57

 >=",

0.56

 минимум

0.56

 LEAST

0.56

 Least

0.55

geq

0.54

Activations Density 0.089%

references to the minimum or least threshold in various contexts

Following the word "least"

at least or least

No Known Activations