INDEX

Explanations

structured data in tables or arrays

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

neval

-0.47

tez

-0.44

 वाला

-0.43

ister

-0.42

PAPER

-0.41

 apel

-0.41

važ

-0.40

<i>

-0.40

MaxSize

-0.39

ָם

-0.39

POSITIVE LOGITS

rungsseite

1.21

AddTagHelper

1.11

 autorytatywna

1.08

 Chwiliwch

1.06

GEBURTSDATUM

1.05

MigrationBuilder

0.97

dafx

0.97

ConstraintMaker

0.97

LookAnd

0.96

sizeCache

0.94

Activations Density 0.157%

structured data in tables or arrays

No Comments

No Known Activations