INDEX

Explanations

mentions of the word "par" 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 @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 Reſ

-1.13

 raiſ

-1.12

 Jefus

-1.11

 Anſ

-1.10

 Monfieur

-1.09

Efq

-1.09

 Majefty

-1.08

 itſelf

-1.07

 Houſe

-1.07

 myſelf

-1.03

POSITIVE LOGITS

par

0.90

par

0.76

box

0.70

II

0.61

From

0.50

sam

0.48

far

0.48

toHaveBeenCalled

0.47

DataPropertyName

0.47

 haut

0.47

Activations Density 0.098%

mentions of the word "par" in various contexts

No Comments

No Known Activations