INDEX

Explanations

specific template-related terminologies in documents

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

AddHtmlAttribute

-0.93

TypedDataSet

-0.90

 Италијани

-0.79

TintMode

-0.78

 initComponents

-0.78

ArrowToggle

-0.74

 typelib

-0.73

ंदीखरीदारी

-0.71

 &___

-0.71

 MenuView

-0.71

POSITIVE LOGITS

glMatrixMode

0.68

ис

0.60

 Langue

0.59

 createStore

0.55

 Pairs

0.54

Pairs

0.53

icorn

0.52

 snippetHide

0.51

OpenHelper

0.50

 radio

0.49

Activations Density 0.009%

specific template-related terminologies in documents

No Comments

No Known Activations