INDEX

Explanations

terms related to adaptation and responsiveness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Rüyada

-0.67

はじめに

-0.60

 ویکی‌پدی

-0.58

 kasarigan

-0.55

 وتسجيلات

-0.55

herjee

-0.55

fromnode

-0.54

Netto

-0.53

Identyfik

-0.53

 propOrder

-0.53

POSITIVE LOGITS

 adapts

1.00

 Adap

0.99

Adap

0.97

 adjusts

0.96

 adap

0.95

 adapt

0.93

Adjust

0.91

 adapting

0.90

adap

0.88

 Adapt

0.87

Activations Density 0.086%

terms related to adaptation and responsiveness

No Comments

No Known Activations