INDEX

Explanations

symbols and punctuation marks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

RenderAtEndOf

-1.28

GEBURTSDATUM

-1.21

 Paglinawan

-1.15

zzleHttp

-1.10

 AssemblyCulture

-1.08

 surla

-1.06

RegistryLite

-1.05

 kasarigan

-1.04

AddTagHelper

-1.03

WebVitals

-1.02

POSITIVE LOGITS

↵↵

0.46

The

0.46

нка

0.44

 This

0.42

®

0.39

 What

0.38

<eos>

0.37

 Clearly

0.36

↵↵↵↵

0.36

Activations Density 0.353%

symbols and punctuation marks

No Comments

No Known Activations