INDEX

Explanations

commands related to document assembly and package inclusion in programming or typesetting languages

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

us

-0.51

or

-0.49

{}

-0.45

big

-0.44

val

-0.44

‏

-0.43

us

-0.43

 orígenes

-0.42

is

-0.42

mm

-0.41

POSITIVE LOGITS

脚注の使い方

1.26

 AssemblyCulture

1.13

 الحره

1.10

 оригіналу

1.08

MessageOf

1.07

Tikang

1.06

tvguidetime

1.02

帖最后由

1.02

 مرئيه

1.01

 NSCoder

1.00

Activations Density 0.045%

commands related to document assembly and package inclusion in programming or typesetting languages

No Comments

No Known Activations