INDEX

Explanations

sections of text that contain numerical data or references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

henswürdigkeiten

-0.63

новништво

-0.63

AndEndTag

-0.61

 BoxDecoration

-0.59

DoubleQuotes

-0.57

Katso

-0.53

addContainerGap

-0.52

انتهای

-0.52

SubType

-0.51

 sanitaires

-0.51

POSITIVE LOGITS

expandindo

0.75

 дописавши

0.67

protoimpl

0.62

 CreateTagHelper

0.60

 gynhyrchwyd

0.59

JspWriter

0.59

 nahilalakip

0.57

TestingModule

0.55

 resourceCulture

0.54

RenderAtEndOf

0.53

Activations Density 0.086%

sections of text that contain numerical data or references

No Comments

No Known Activations