INDEX

Explanations

keywords related to criteria and conditions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

modb

-0.56

govine

-0.52

 Zweifel

-0.51

 privato

-0.50

 foncé

-0.49

 Normdatei

-0.44

sĩ

-0.43

 abstrait

-0.43

tiftung

-0.43

 средства

-0.42

POSITIVE LOGITS

tagHelper

0.76

 مشين

0.71

rungsseite

0.71

UnusedPrivate

0.70

AutoresizingMask

0.69

 utafitiHapana

0.67

EndGlobalSection

0.67

WriteTagHelper

0.65

kuuta

0.63

 ModelExpression

0.62

Activations Density 0.215%

keywords related to criteria and conditions in various contexts

No Comments

No Known Activations