INDEX

Explanations

terms and identifiers related to minimum values in data and programming contexts

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

min

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

 atmósfera

-0.57

>{@

-0.57

แก่

-0.56

retVal

-0.55

 carretera

-0.54

URLException

-0.54

 errorCode

-0.53

cetines

-0.53

 callable

-0.53

 statusCode

-0.53

POSITIVE LOGITS

min

0.89

Min

0.86

Min

0.82

MIN

0.81

min

0.79

getMin

0.73

MIN

0.72

setMin

0.70

minX

0.68

 getMin

0.66

Activations Density 0.021%

terms and identifiers related to minimum values in data and programming contexts

min

No Comments

No Known Activations