INDEX

Explanations

terms related to minimum values, minimization, and associated processes

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

The token "min"

np_acts-logits-general · gemini-2.0-flash

min

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 AssemblyCompany

-0.53

 consultato

-0.52

ToMany

-0.50

PositiveButton

-0.49



-0.48

spacer

-0.48

 fahren

-0.47

LITERAL

-0.46

OwnProperty

-0.46

 anello

-0.45

POSITIVE LOGITS

MIN

1.02

MIN

0.98

 getMin

0.90

min

0.89

Min

0.87

StructEnd

0.87

min

0.84

Min

0.82

 Mins

0.80

InvalidProtocol

0.79

Activations Density 0.188%

terms related to minimum values, minimization, and associated processes

The token "min"

min

No Comments

No Known Activations