INDEX

Explanations

phrases related to statistical evaluation and classification of agreement levels

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

degree or quality

np_acts-logits-general · gemini-2.0-flash

levels of quality or agreement

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

 Wikimedijinoj

-0.75

 EconPapers

-0.64

исленность

-0.59

Bibliograf

-0.58

usammen

-0.56

unmodifiable

-0.55

 Vitamina

-0.52

assertArray

-0.52

 sworn

-0.50

fortunes

-0.49

POSITIVE LOGITS

 moderate

1.32

 medium

1.20

 Moderate

1.19

 moderately

1.14

 Medium

1.12

medium

1.08

Moderate

1.06

 intermediate

1.05

 Intermediate

1.04

Medium

1.03

Activations Density 0.720%

phrases related to statistical evaluation and classification of agreement levels

degree or quality

levels of quality or agreement

No Comments

No Known Activations