INDEX

Explanations

references to numerical values or representations in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_mlp_out

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

 perju

-0.45

GBT

-0.45

[]>

-0.43

 lemp

-0.42

Im

-0.42

UnsafeEnabled

-0.41

 pasto

-0.41

 programmes

-0.41

<unused63>

-0.40

Int

-0.40

POSITIVE LOGITS

AddTagHelper

0.75

jspx

0.71

AddHtmlAttribute

0.66

stateProvider

0.65

 contextLoads

0.65

 transfieras

0.65

 inflater

0.64

 صوتيه

0.63

getSystemService

0.63

+#+

0.62

Activations Density 0.224%

references to numerical values or representations in scientific contexts

No Comments

No Known Activations