INDEX

Explanations

numerical values and formatting in textual data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

EnumType

-0.51

 rent

-0.47

forRoot

-0.47

-0.44

 algumas

-0.44

 Normdatei

-0.43

 algunas

-0.43

PhysRevD

-0.43

 typelib

-0.42

 stør

-0.40

POSITIVE LOGITS

 pleaſure

0.89

 Monfieur

0.84

 ſtate

0.83

 raiſ

0.82

Efq

0.82

 diſt

0.81

 reaſon

0.81

 purpoſe

0.81

 leaſt

0.79

 ſtand

0.78

Activations Density 0.189%

numerical values and formatting in textual data

No Comments

No Known Activations