INDEX

Explanations

references to numerical values or statistical data

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

Numbers separated by commas

np_acts-logits-general · gemini-2.0-flash

numerical sequences and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 darkest

-0.57

 dark

-0.56

 darkness

-0.55

 nifer

-0.50

dark

-0.50

 Darkness

-0.49

 heav

-0.48

 fré

-0.48

 Ness

-0.47

 rough

-0.47

POSITIVE LOGITS

LookAnd

1.00

 gynhyrchwyd

0.86

 समीक्षक

0.86

DockStyle

0.83

SourceChecksum

0.82

StructEnd

0.81

 AssemblyCulture

0.80

addCriterion

0.78

 invokingState

0.78

IUrlHelper

0.76

Activations Density 0.487%

references to numerical values or statistical data

Numbers separated by commas

numerical sequences and references

No Comments

No Known Activations