INDEX

Explanations

references to locations or venues in texts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 utafitiHapana

-1.01

OGND

-1.00

featureID

-0.95

tvguidetime

-0.93

SBATCH

-0.89

QMetaType

-0.89

 оригіналу

-0.89

 فريبيس

-0.88

ReusableCell

-0.86

 Administrativna

-0.85

POSITIVE LOGITS

at

0.98

0.67

by

0.65

 tại

0.64

At

0.61

 within

0.58

At

0.57

 including

0.54

0.53

in

0.53

Activations Density 0.219%

references to locations or venues in texts

No Comments

No Known Activations