INDEX

Explanations

mathematical expressions and notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

ReusableCell

-0.51

 most

-0.43

ic

-0.43

mitglied

-0.43

IC

-0.42

 program

-0.42

 research

-0.42

ent

-0.42

 technology

-0.41

Basic

-0.41

POSITIVE LOGITS

 <=",

1.12

MigrationBuilder

1.02

aarrggbb

0.94

RegressionTest

0.94

IsContent

0.92

 propOrder

0.92

SharedDtor

0.89

 >=",

0.89

ValueStyle

0.88

TagMode

0.87

Activations Density 0.783%

mathematical expressions and notations

No Comments

No Known Activations