INDEX

Explanations

HTML and XML tags

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

HTML code context

np_acts-logits-general · gemini-2.0-flash

HTML structure tags

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

发表于

-0.61

 CURIAM

-0.59

pulumi

-0.52

 Cell

-0.51

atshirt

-0.50

 незавершена

-0.49

GraphicsUnit

-0.49

wps

-0.48

XmlEnum

-0.48

 Процитовано

-0.47

POSITIVE LOGITS

parsedMessage

0.70

 pleaſure

0.66

 ſche

0.63

 Majefty

0.60

 ſever

0.60

 OFDb

0.60

 houſe

0.58

 poffible

0.56

addCriterion

0.55

body

0.55

Activations Density 0.133%

HTML and XML tags

HTML code context

HTML structure tags

No Comments

No Known Activations